ksaserver-goldseam
Registry code: c6957a096d01e462
GoldSeam is the marketplace for teaching, training and learning: one endpoint where you explore what postsecondary organizations offer, compare what actually differs between them, and help a person engage with the organization that decides. Every answer names the contract that produced it and the snapshot it was read from, and an absence is stated rather than filled in. CourseShelf — colleges and what they teach, from the institutions' own published catalogs: a school, its programs, its courses, its checklists (the requirements for an award), its catalogs and its published policies. GoldCheck…
- endpoint
- https://goldseam.ksaworks.com/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is ksaserver-goldseam live?
- Yes — it answered the hub's last check (checked 20m ago). It answered 100% of checks over the last 30 days.
- Is ksaserver-goldseam free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does ksaserver-goldseam have?
- 51 tools: compare_destinations, compare_program_checklists, certifications_for_occupation, certifications_for_program, get_certification, comparability_for_learning_unit, get_learning_unit, compare_my_school, ….
- Is ksaserver-goldseam safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.5%· all time 99.5%
last good check
of 51 tools
- down → live
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- live → degraded· timeout after 20000ms
- topic
- education & learning
- used for
- find a college major
- find schools offering a program
- compare program requirements
- check course transfer agreements
- takes → gives
- text, documents → data
- tools
- 23 reads2 changes data
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_dictionary_summary open 5h ago
What does the KSA Dictionary hold? The words and meanings it places, the governed terms, the O*NET content-model elements, the link words and the CIP-SOC crosswalk, each with its own version and build date where the layer publishes one, and an honest not held where it does not. Read as published at boot, never computed at request time, and never a word lookup: for one word use resolve_term. The words it holds are those it places; it is not all of WordNet, and the answer says so.
{ "type": "object", "properties": {} }arguments 4 linesfind_pathways open 17h ago
Which pathways are held? Optional title words, an agreement id, or a checklist id. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "description": "Optional pathway title words" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "agreement_id": { "type": "string", "description": "Optional: the agreement a pathway rests on" }, "checklist_id": { "type": "string", "description": "Optional: the checklist a pathway follows" } } }arguments 25 linesfind_agreements reads open 5h ago
Which articulation or transfer agreements are held? Optional title words, or an institution's UNITID as a party. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "description": "Optional agreement title words" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "description": "Optional: an institution party's IPEDS UNITID" } } }arguments 21 linesget_courseshelf_summary open 7h ago
What does CourseShelf hold? From the records published with the build, read as published and never computed: per catalog area, how many institutions have loaded content and how many records were loaded; every table's row count; organizations by sector; the census of the whole index with its verdicts; and per-state counts and per-school verdicts where the build publishes them. Anything not published for this build is said so. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": {} }arguments 4 linesfind_institution open 19h ago
Which institution is this? A name fragment or an IPEDS UNITID answers with the institution's identity, sector, identifiers with their sources, and how many programs, checklists, and learning units its published catalog holds here. A state lists that state's institutions by name; with no name and no state, the answer is the states that hold institutions, each with its count. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "city": { "type": "string", "examples": [ "Denison" ], "description": "Optional city, one of a state answer's cities, e.g. Denison" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "examples": [ "Grayson", "225070" ], "description": "Name fragment or IPEDS UNITID, e.g. Denver or 127060" }, "state": { "type": "string", "examples": [ "TX" ], "description": "Optional two-letter state, e.g. TX: that state's institutions, those with a catalog held first; the answer lists the state's cities" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 35 linesfind_comparability reads open 20m ago
Which comparability bundles (published transfer rules) are held? Optional receiving institution UNITID, agreement id, or a learning unit that appears as a source or substitute. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "description": "Optional: the receiving institution's IPEDS UNITID" }, "agreement_id": { "type": "string", "description": "Optional: the agreement that states it" }, "learning_unit_id": { "type": "string", "description": "Optional: a course named in it" } } }arguments 25 lineslist_issuers open 7h ago
The issuing organizations, optionally filtered by a name query.
{ "type": "object", "required": [], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "query": { "type": "string", "examples": [ "IBM", "nursing" ], "description": "Optional: part of an organization's name" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 22 linessearch_programs_and_learning_units reads open 7h ago
Which programs or courses match, and where? Words, a subject (CIP family, or unknown), a course subject prefix, a credential class, an award as published, and a school's state, city, type or UNITID answer with product cards (name, award, length and college when held, school and city, subject, checklist size, and what the program leads to through the CIP-SOC crosswalk) and the counts to refine by. Courses across every school need words of 3 or more characters; words held by very many courses need a state, city or school. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "cip": { "description": "Optional: programs with this six-digit CIP code (e.g. 48.0508), a comma-separated list, or an array of codes" }, "city": { "type": "string", "description": "Optional city, one of a state answer's cities" }, "code": { "type": "string", "description": "Optional, courses only: a course code as printed, e.g. ZOO 2015; lists that code at every school, or within the state, city or school given" }, "type": { "type": "string", "examples": [ "program" ], "description": "program (the default) or learning_unit" }, "award": { "type": "string", "examples": [ "Certificate" ], "description": "Optional award exactly as published, one of the answer's awards" }, "limit": { "type": "integer", "description": "Optional page size (default 10, at most 50)" }, "place": { "type": "string", "description": "Optional: a place the question names, read as a state (name or code), a city, or a school, e.g. Wyoming or Casper" }, "query": { "type": "string", "examples": [ "nursing" ], "description": "Words: a program's name or award, or a course's title" }, "state": { "type": "string", "examples": [ "TX" ], "description": "Optional two-letter state" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "sector": { "type": "string", "description": "Optional school type as IPEDS labels it, e.g. public 2-year" }, "unitid": { "type": "string", "description": "Optional: one school's IPEDS UNITID" }, "subject": { "type": "string", "description": "Optional CIP family (two digits, e.g. 51) or unknown" }, "credential": { "type": "string", "description": "Optional, programs only: a credential class, one of the answer's credential values (e.g. ceterms:AssociateDegree), or none" }, "subject_code": { "type": "string", "description": "Optional: a course subject prefix, e.g. NURS, one of the answer's subject codes. A course's own prefix as printed, or a prefix a program's checklist requires" } } }arguments 76 linescompare_destinations reads unknown 36h ago
Line up 2 to 6 destination occupations side by side from one occupation: the bridge size (credential only, or the program bridges' awards as published), O*NET demand (median wage, outlook, bright outlook) and the evidence classes of the roads. Each cell is copied or counted, never scored.
{ "type": "object", "required": [ "from_soc", "to_socs" ], "properties": { "to_socs": { "type": "array", "items": { "type": "string" }, "examples": [ [ "51-4122", "17-3029" ] ], "description": "2 to 6 destination SOC codes, e.g. from find_transitions" }, "from_soc": { "type": "string", "examples": [ "51-4121" ], "description": "The occupation compared from, e.g. 51-4121" } } }arguments 29 linescompare_program_checklists reads unknown 36h ago
Compare what a program takes at several institutions: for each IPEDS UNITID, that institution's published checklist for the program (requirement groups, items, published credit strings — the work effort) beside its published tuition and fee policy (the cost). Schedule is stated not held. Nothing is summed or computed by the service; an institution, checklist, or cost the catalogs do not hold is stated as such. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitids", "program" ], "properties": { "detail": { "type": "string", "examples": [ "summary" ], "description": "Optional: full (the default: every requirement group and item) or summary (per checklist its program, award, year, credits and group and item counts, with each school's College Scorecard tuition)" }, "program": { "type": "string", "examples": [ "Welding" ], "description": "Program or award words to match, e.g. nursing or Bachelor of Science in Nursing" }, "unitids": { "type": "array", "items": { "type": "string" }, "examples": [ [ "225070" ] ], "description": "1 to 10 IPEDS UNITIDs, e.g. [\"100663\", \"127060\"]; answered 5 institutions per call, up to 3 checklists each" }, "institution_offset": { "type": "integer", "description": "Optional: the next_institution_offset from a previous answer, for the next 5 institutions" } } }arguments 39 linescertifications_for_occupation reads unknown 43h ago
What certifications serve this occupation? SOC-keyed lookup (dashed SOC accepted with or without the O*NET .00 suffix).
{ "type": "object", "required": [ "soc" ], "properties": { "soc": { "type": "string", "examples": [ "29-1141", "47-2111" ], "description": "An occupation code (SOC), e.g. 29-1141 for Registered Nurses or 47-2111 for Electricians — don't know it? search by the job name instead" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 24 linescertifications_for_program unknown 43h ago
Broad academic cross-reference by instructional program (CIP). A deliberately broader, lower-precision question than an occupation lookup — never its peer (contract § 4).
{ "type": "object", "required": [ "cip" ], "properties": { "cip": { "type": "string", "examples": [ "51.3801", "47.0201" ], "description": "A college program code (CIP), e.g. 51.3801 for Registered Nursing or 47.0201 for HVAC technology" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 24 linesget_certification unknown 19h ago
Everything held about one certification: issuer and issuer domain, occupations served, exam and renewal requirements, education-or-experience routes, Credential Engine registry identity where held, and the basis and source URL for the claim.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "examples": [ "LU_CERT_ONET_13108200_8F3480AC7A" ], "description": "A certification id, copied from a search result's id field" } } }arguments 15 linescomparability_for_learning_unit unknown 12h ago
Where does this course land at other schools, and what lands on it (exams included)? The published transfer rules for one course: the rules CourseShelf holds first (a school's own catalog, CourseAtlas), then CourseAtlas's direct rules read live. Each rule names its source authority, source_url and band; comparable, never equivalent. What lands on a course is answered from the held rules only. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "code": { "type": "string", "description": "The course code as printed, e.g. HIST 201" }, "limit": { "type": "integer", "description": "Optional page size per list (default 10, at most 50)" }, "title": { "type": "string", "description": "Or: the course title, matched exactly" }, "offset": { "type": "integer", "description": "Optional: the offset of the next page" }, "school": { "type": "string", "description": "Or: the course's school, by name (with code or title)" }, "unitid": { "type": "string", "description": "Or: the course's school, by IPEDS UNITID (with code or title)" }, "direction": { "enum": [ "lands_as", "lands_on", "both" ], "type": "string", "description": "lands_as: where it lands; lands_on: what lands on it; both (default)" }, "target_unitid": { "type": "string", "description": "Optional: narrow where it lands to one receiving school (IPEDS UNITID)" }, "learning_unit_id": { "type": "string", "description": "The course, by its learning unit id" } } }arguments 46 linesget_learning_unit reads unknown 12h ago
One course whole: its row, prerequisites and corequisites, aliases, terms offered, articulation statements and comparable members — each linked course resolved or stated unresolved, never guessed — plus the transfer frameworks it maps to. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "learning_unit_id" ], "properties": { "learning_unit_id": { "type": "string", "examples": [ "LU_course_225070_ENGL1301_20262027" ], "description": "A learning unit id from learning_units or get_checklist" } } }arguments 15 linescompare_my_school unknown 12h ago
Which of these schools is better for me? Two to five schools, one major and a level, side by side: program and award, credits required verbatim, requirements compared line by line, and — when the person offers their courses and exam scores — what each school's own published rules would count them for, with GoldCheck's states and reasons carried through unchanged. Credits left is reduced only by items a school's own rules cover; an unknown item, or an inference, never reduces it. Cost, earnings, debt with its 10-year monthly payment beside it, and payback in months where both inputs are published; where either is missing, payback is not computed and the missing input is named. The comparison never ranks: no score is invented to decide for the person.
{ "type": "object", "required": [ "unitids", "major", "level" ], "properties": { "held": { "type": "array", "items": { "type": "object" }, "description": "Optional: the same shape will_my_credits_transfer takes — an exam { program, exam, score } or a course { unitid or school, code }" }, "level": { "type": "string", "description": "The credential level" }, "major": { "type": "string", "description": "The major: a major_minor_id or a CIP code" }, "package": { "type": "object", "description": "Optional: the agent-held GoldRibbon package. GoldSeam stores no copy of it" }, "unitids": { "type": "array", "items": { "type": "string" }, "examples": [ [ "240505", "240628" ] ], "description": "2 to 5 schools, by IPEDS UNITID" } } }arguments 42 lineslearning_units reads unknown 22h ago
What courses does this institution publish? Filter by subject abbreviation, course code (spaces and case ignored), or title words; each course carries its published credit string verbatim (ranges stay ranges), edition, and the captured page. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitid" ], "properties": { "code": { "type": "string", "description": "Optional course code, e.g. BIO 201" }, "limit": { "type": "integer", "description": "Optional page size (default 50, at most 100)" }, "query": { "type": "string", "description": "Optional title words" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "examples": [ "225070" ], "description": "The institution's IPEDS UNITID" }, "subject": { "type": "string", "examples": [ "RNSG" ], "description": "Optional subject abbreviation, e.g. BIO" }, "unit_type": { "type": "string", "description": "Optional learning-unit type, one of the answer's unit_types, e.g. course" } } }arguments 42 linesfind_transfer_frameworks reads unknown never probed
Which statewide or compact transfer frameworks are held? Optional name or jurisdiction words. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "description": "Optional framework name or jurisdiction words" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 17 linesget_transfer_framework unknown never probed
One transfer framework: its row, authority, codes with their meanings, and the courses mapped to it (resolved). Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "framework_id" ], "properties": { "framework_id": { "type": "string", "description": "A framework id from find_transfer_frameworks" } } }arguments 12 linesassemble_my_work_and_credentials changes data unknown never probed
Read a person's resume, LinkedIn export, certificates, military records and apprenticeship records into their evidence package: each file's text and status, and the credential signals the certificate, military and apprenticeship documents carry. Ask the person for each file. This assembles; the Selfie is my_selfie_ksa_view. Nothing is stored: the answer returns the package for the agent to keep.
{ "type": "object", "required": [ "files" ], "properties": { "files": { "type": "array", "items": { "type": "object", "required": [ "slot", "filename", "content_base64" ], "properties": { "slot": { "enum": [ "resume", "linkedin_file", "certs", "military", "apprentice" ], "type": "string" }, "filename": { "type": "string" }, "content_base64": { "type": "string", "description": "The file's bytes, base64. A call's files total at most about 1.5 MB; send more over several calls with the same package." } } }, "description": "1 or more files" }, "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." }, "linkedin_url": { "type": "string", "description": "Optional: the person's LinkedIn profile address" } } }arguments 47 linessuggest_credit_for_my_learning unknown never probed
Where is a person in the program they are aiming for, and what may their learning meet? Name the program with `checklist_id` (find it with find_programs at that school) and the answer is that program's checklist line by line: the lines their claims may meet, each with the claim, how well it is corroborated and every link cited; the lines a transfer answer in their package already covers; and the lines still needed. Learning no line matches stands as block credit. Without a program, no course is suggested and the claims stand as block credit. Each suggestion is a case to put to the school's prior learning review, never a promise: say may, never will. Nothing is stored: the answer returns the package with the suggestions for the agent to keep.
{ "type": "object", "required": [ "package", "target_unitid" ], "properties": { "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." }, "language": { "enum": [ "en", "es", "fr" ], "type": "string" }, "aspiration": { "type": "string", "description": "Optional: what the person is aiming for" }, "checklist_id": { "type": "string", "examples": [ "CK_225070_05e6e123" ], "description": "The program the person is aiming for, from find_programs or find_checklists at that school. Its lines are the only courses considered; without it no course is suggested." }, "target_unitid": { "type": "string", "examples": [ "240620" ], "description": "The school's IPEDS UNITID, e.g. 240620" } } }arguments 39 linesfind_checklists unknown 26h ago
Which checklists — the generic itinerary of requirements for an award — does this institution publish? Optional award words or a program id narrow them; pass one to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitid" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "description": "Optional award words, e.g. welding" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "examples": [ "225070" ], "description": "The institution's IPEDS UNITID" }, "program_id": { "type": "string", "description": "Optional: one program's id" } } }arguments 31 linesexpand_term unknown 31h ago
What is this word, upward? Walks the WordNet is-a (hypernym) chain meaning to parent meaning, from the word's KSA-mapped sense toward its broader categories, so every step stays in the sense it started in. Each step carries its definition (gloss) and synonyms.
{ "type": "object", "required": [ "term" ], "properties": { "term": { "type": "string", "examples": [ "carpentry", "nursing" ], "description": "A word to see what broader kind of thing it is, e.g. carpentry" } } }arguments 16 linesdraft_my_claims unknown never probed
Draft the credit claims a person's evidence supports, from their package (after my_selfie_ksa_view): each claim quotes the document it rests on. They are drafts for the person to keep, affirm or decline (set each claim's confidence to ratified, affirmed or declined in the package); the AI never affirms a claim. Give the school they are thinking of as `school` so its catalog is made ready for suggest_credit_for_my_learning. Nothing is stored: the answer returns the package for the agent to keep.
{ "type": "object", "required": [ "package" ], "properties": { "school": { "type": "string", "description": "Optional: the school they are thinking of, a name or IPEDS UNITID; its catalog is made ready for the suggestions" }, "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." }, "language": { "enum": [ "en", "es", "fr" ], "type": "string" }, "aspiration": { "type": "string", "description": "Optional: what the person is aiming for" } } }arguments 28 linesget_catalog reads unknown 18d ago
One catalog edition: its row, the institutions that use it (and whom it is shared from), and how many programs it holds. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "catalog_id" ], "properties": { "catalog_id": { "type": "string", "description": "A catalog id from find_catalogs" } } }arguments 12 linesresolve_term unknown 33h ago
Where does a word place in the KSA model? The KSA Dictionary is the shared vocabulary that defines the terms a learner uses to assert what they know, do, and are — and the terms a learning offering uses to express what it comprises — so both sides resolve to the same identifiers, never spelling matches. Answers from three linked layers (governed lexicon, O*NET content model, WordNet-derived index), each placement attributed to its layer with provenance; the WordNet placement carries the word's definition (gloss) and synonyms.
{ "type": "object", "required": [ "term" ], "properties": { "term": { "type": "string", "examples": [ "carpentry", "mathematics", "welding" ], "description": "A word for something a person knows or can do, e.g. carpentry or mathematics" } } }arguments 17 linescrosswalk_code reads unknown 33h ago
What does this code cross to? Auto-detects the family — dotted CIP (52.0201) or dashed SOC (11-1021, O*NET .00 suffix accepted) — and answers the other family's codes and titles from the federal CIP-SOC crosswalk.
{ "type": "object", "required": [ "code" ], "properties": { "code": { "type": "string", "examples": [ "51.3801", "29-1141" ], "description": "A college program code (CIP, e.g. 51.3801) or an occupation code (SOC, e.g. 29-1141)" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 24 linesfind_my_major reads unknown 2h ago
What should I study? For a person's own words — an interest, a subject or a job — or a job code (SOC), the majors that answer. Each major carries its plain definition (NCES verbatim), the award levels it is conferred at (IPEDS AWLEVEL, each completers flag in its own field and never summed), how many schools offer it nationally, the jobs it leads to through the federal CIP-SOC crosswalk, and its related majors — same series, same family, or sharing a named occupation. Words resolve through the KSA Dictionary, never by spelling match; words that match nothing are told so with the closest words the Dictionary holds. The count for a person's own state is stated not held: the per-school IPEDS rows are not in this publish.
{ "type": "object", "anyOf": [ { "required": [ "words" ] }, { "required": [ "soc" ] } ], "properties": { "soc": { "type": "string", "examples": [ "29-1141" ], "description": "Or a job code (SOC), e.g. 29-1141 for Registered Nurses; every major the federal crosswalk ties to it answers" }, "level": { "type": "string", "description": "Optional award level to narrow to, e.g. certificate, associate or bachelor's" }, "limit": { "type": "integer", "description": "Optional page size (default 10, at most 25)" }, "state": { "type": "string", "description": "Optional two-letter state, for the school counts" }, "words": { "type": "string", "examples": [ "carpentry" ], "description": "The person's own words: an interest, a subject, or a job, e.g. I like fixing things" }, "offset": { "type": "integer", "description": "Optional: the offset of the next page" } } }arguments 47 linesget_checklist reads unknown 17h ago
What does this award require? One checklist: its requirement groups (every header and full item count), each group's items with published credit strings, alternatives, and — where an item resolved to a course — that course's own code, title, and published credits, attributed to the course. Items come in pages across the groups; the answer states items_total and next_item_offset. Every row names the captured page it came from. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "checklist_id" ], "properties": { "item_limit": { "type": "integer", "description": "Optional items per page (default 60, at most 150)" }, "item_offset": { "type": "integer", "description": "Optional: the next_item_offset from a previous answer" }, "checklist_id": { "type": "string", "examples": [ "CK_225070_05e6e123" ], "description": "A checklist id from programs_for_institution or compare_program_checklists" } } }arguments 23 linesmy_selfie_ksa_view reads unknown 2h ago
The person's Selfie from their evidence package: the seven dimensions (skills, knowledge, abilities and more) as the evidence shows them, each item citing the file, the occupation O*NET describes, or the life experience it came from, plus what could not be placed. It mirrors, for the person to confirm, refine or reject; it is never a grade or a credit decision. The person's placements and dismissals in the package's selfie.learner_decisions are honored. Nothing is stored: the answer returns the package with the Selfie for the agent to keep.
{ "type": "object", "required": [ "package" ], "properties": { "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." }, "language": { "enum": [ "en", "es", "fr" ], "type": "string" }, "aspiration": { "type": "string", "description": "Optional: what the person is aiming for" } } }arguments 24 linesoccupations_for_certification unknown 2h ago
What occupations does this certification serve?
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "examples": [ "LU_CERT_ONET_13108200_8F3480AC7A" ], "description": "A certification id, copied from a search result's id field" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 23 linesfind_programs reads unknown 22h ago
Which programs match these words, across institutions? Program or award words (optionally one institution's UNITID) answer with each program's award, CIP, published credit figure verbatim, edition, source page and institution. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "query" ], "properties": { "city": { "type": "string", "description": "Optional city: programs at that city's institutions" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "examples": [ "Welding" ], "description": "Program or award words, e.g. welding or nursing" }, "state": { "type": "string", "description": "Optional two-letter state: programs at that state's institutions" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "description": "Optional: one institution's IPEDS UNITID" } } }arguments 35 linesget_pathway unknown 9h ago
One pathway: its row and the checklist and agreement it links. Contacts name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "pathway_id" ], "properties": { "pathway_id": { "type": "string", "description": "A pathway id from find_pathways" } } }arguments 12 linesget_policy unknown 9h ago
One published academic policy: its section, verbatim text, page, edition and source. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "policy_id" ], "properties": { "policy_id": { "type": "string", "description": "A policy id from find_policies" } } }arguments 12 linesget_program reads unknown 9h ago
One program whole: its row, identifiers, offerings (campus resolved), its institution, and the checklists that lead to its award — pass one to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "program_id" ], "properties": { "program_id": { "type": "string", "examples": [ "PG_225070_8c96bb26" ], "description": "A program id from programs_for_institution or find_programs" } } }arguments 15 linesfind_transitions unknown 14h ago
Where can this occupation lead? For a SOC code: destination occupations, each with its typed roads (published by O*NET or by a credential serving both; mapped through the CIP-SOC crosswalk), each road with its source, basis and its class's karat; the bridges (credentials with their exam, education and experience conditions, and programs with checklists nearest the state given); and demand as O*NET publishes it. Roads only, no person data.
{ "type": "object", "anyOf": [ { "required": [ "from_soc" ] }, { "required": [ "from" ] } ], "properties": { "from": { "type": "string", "description": "Or the job in everyday words, e.g. welder; several matching occupations answer candidates to pick from" }, "class": { "type": "string", "description": "Optional: only destinations with a road of this class (published, mapped)" }, "limit": { "type": "integer", "description": "Optional page size (default 10, at most 25)" }, "state": { "type": "string", "description": "Optional two-letter state for the program bridges" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "prefer": { "type": "string", "description": "Optional preference such as less physical; answered not held when O*NET work context is not held" }, "from_soc": { "type": "string", "examples": [ "51-4121" ], "description": "The occupation's SOC code, e.g. 51-4121 (an O*NET .00 code is accepted)" } } }arguments 48 linesfind_my_school reads unknown 24h ago
Where can I study this? A match-up, not a dump: for a major and a level, the schools that award it, ranked by how many of the person's own criteria each one meets, with met, not met and not testable kept as three different results — a school that does not publish a fact is not testable on it, never failed. Each criterion names the source that decided it, each school carries its own program, award, credits required, cost, earnings, debt and whether it can be done online, and a filter only ever excludes on a fact we hold. The answer states its ranking rule and never recommends a school. TODAY the candidate set is the schools CourseShelf has captured a program for, not yet every school IPEDS lists, and every answer opens by saying so.
{ "type": "object", "required": [ "major", "level" ], "properties": { "city": { "type": "string", "description": "Optional city" }, "near": { "type": "string", "description": "Optional: a place and a distance, e.g. Casper WY within 50 miles" }, "award": { "type": "string", "description": "Optional award title or credential class" }, "level": { "type": "string", "examples": [ "associate" ], "description": "The credential level, e.g. certificate, associate or bachelor's" }, "limit": { "type": "integer", "description": "Optional page size (default 10, at most 25)" }, "major": { "type": "string", "examples": [ "CIP:51.3801" ], "description": "The major: a major_minor_id (e.g. CIP:51.3801) or a CIP code" }, "state": { "type": "string", "description": "Optional two-letter state. With no state, city or place the answer is national and says so" }, "offset": { "type": "integer", "description": "Optional: the offset of the next page" }, "sector": { "type": "string", "description": "Optional school type as IPEDS labels it, e.g. public 2-year" }, "cost_max": { "type": "number", "description": "Optional: the most the person will pay. A school that publishes no cost is not removed by it — it is ranked below and marked not testable on cost" }, "delivery": { "type": "string", "description": "Optional: in person, hybrid or online" }, "also_offers": { "type": "array", "items": { "type": "string" }, "description": "Optional other subjects or majors the school should also offer" }, "with_checklist": { "type": "boolean", "description": "Optional: only schools whose requirements CourseShelf holds" }, "exclude_untestable": { "type": "boolean", "description": "Optional strict exclusion, off by default: remove schools that do not publish one of the criteria. The answer then says how many were removed and by which criterion" } } }arguments 74 lineswill_my_credits_transfer unknown never probed
Will my prior credits apply as credit at my target school? For each thing a person holds (an AP, CLEP or IB exam and its score, or a course taken at a school) the target school's own published transfer rules (CourseAtlas) and CollegeBoard's reported AP policy, in three states: covered (a rule carries it to a course at the target), missing (the target's own rule needs a higher score), unknown (no rule held; never a guess). Each covered item names the course it lands as, every rule with its minimum score and dates, how many rules agree, and the target's programs whose checklists require that course. A case to argue, not a verdict; recognition is the school's act. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "held", "target_unitid" ], "properties": { "held": { "type": "array", "items": { "type": "object" }, "examples": [ [ { "exam": "United States History", "score": 3, "program": "AP" } ] ], "description": "1 to 20 things held: an exam { program: AP|CLEP|IB, exam: its code (e.g. AP 3700) or title (e.g. United States History), score }, or a course { unitid or school, code as printed (e.g. HIS 110) }" }, "checklist_id": { "type": "string", "description": "Optional: the target program's checklist id; the answer then names the lines each covered item addresses" }, "target_unitid": { "type": "string", "examples": [ "216038" ], "description": "The target school's IPEDS UNITID, e.g. 216038" } } }arguments 36 linesget_agreement unknown 19h ago
One agreement: its row, its parties (organizations resolved), and the pathways, comparability bundles and checklists that cite it. Signatories name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "agreement_id" ], "properties": { "agreement_id": { "type": "string", "description": "An agreement id from find_agreements" } } }arguments 12 lineschecklists_requiring_learning_unit reads unknown 39h ago
Which checklists require this course? Each requirement item that resolved to it, with its checklist id, award and group heading. Items that did not resolve to a course are never guessed into this list. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "learning_unit_id" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "learning_unit_id": { "type": "string", "examples": [ "LU_course_225070_ENGL1301_20262027" ], "description": "A learning unit id from learning_units or get_learning_unit" } } }arguments 23 linesrelated_certifications reads unknown 39h ago
What else serves the same occupation? Traverses on SOC only — a certification sharing solely an instructional program (CIP) is not related (contract § 4).
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "examples": [ "LU_CERT_ONET_29114100_50CD2891D4" ], "description": "A certification id to find others like it, copied from a search result's id field" }, "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 23 linesget_institution reads unknown 20m ago
Everything held about one institution: its identity row, identifiers, addresses, websites, accreditations, relationships, identity history, published costs and calendar dates, each table under its own name, with counts of its programs, courses, checklists, catalogs, policies and agreements and the service that lists each. Contacts name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "anyOf": [ { "required": [ "organization_id" ] }, { "required": [ "unitid" ] } ], "properties": { "unitid": { "type": "string", "description": "Or its IPEDS UNITID instead, e.g. 225070" }, "organization_id": { "type": "string", "examples": [ "ORG_225070" ], "description": "The institution's organization id from find_institution, e.g. ORG_225070" } } }arguments 28 linesfind_my_best_pathway unknown 5h ago
What's my best way there? For a goal — a major or a job — and what the person brings (courses, exams, their Competency Selfie, work and life experience), the paths to it, each saying WHY it ranks where it does and naming the figures that moved it. The steps appear only where an agreement or pathway document states them, never assembled from award levels alone. Every item the person brought is marked counted, not counted or needs review and appears in the answer: nothing is dropped silently. A path missing an input is ranked with that gap named rather than penalised invisibly.
{ "type": "object", "required": [ "goal", "level" ], "properties": { "goal": { "type": "string", "examples": [ "29-1141" ], "description": "A major (a major_minor_id or CIP) or a job (a SOC code)" }, "held": { "type": "array", "items": { "type": "object" }, "description": "Optional: courses and exams, the shape will_my_credits_transfer takes" }, "level": { "type": "string", "description": "The level the person wants" }, "limit": { "type": "integer", "description": "Optional page size (default 10, at most 25)" }, "state": { "type": "string", "description": "Optional two-letter state: where they are" }, "package": { "type": "object", "description": "Optional: the agent-held GoldRibbon package, read by suggest_credit_for_my_learning. GoldSeam stores no copy" } } }arguments 39 linesassert_my_life_experiences unknown 20m ago
Record what a person says they have done outside school and work (family, clubs, sports, faith, travel, self-taught projects, challenges) in their evidence package, each placed in a Selfie dimension by the KSA classifier or left unresolved, never defaulted. These are the person's own statements, kept apart from formal education. Nothing is stored: the answer returns the package for the agent to keep.
{ "type": "object", "required": [ "entries" ], "properties": { "entries": { "type": "array", "items": { "type": "object", "required": [ "category", "activity" ], "properties": { "weight": { "enum": [ "occasional", "regular", "central" ], "type": "string" }, "activity": { "type": "string", "description": "What the person did, in their words" }, "category": { "enum": [ "passions", "sports", "clubs", "faith", "family", "selftaught", "travel", "challenges", "other" ], "type": "string" }, "difficulty": { "enum": [ "remember", "understand", "apply", "analyze", "evaluate", "create" ], "type": "string" }, "elaboration": { "type": "string" }, "life_period": { "enum": [ "childhood", "adolescence", "emerging_adult", "early_adult", "midlife", "experienced", "later_life" ], "type": "string" } } }, "description": "1 to 20 life experiences" }, "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." } } }arguments 77 linesprograms_for_institution reads unknown 46h ago
What programs does this institution publish? Award, credential class, CIP, the published credit figure verbatim, catalog edition, the captured page each came from, and the checklist ids to pass to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitid" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 100, at most 200)" }, "query": { "type": "string", "description": "Optional program or award words to filter by" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "examples": [ "225070" ], "description": "The institution's IPEDS UNITID" } } }arguments 27 linesget_comparability reads unknown 14h ago
One comparability bundle: its row (credits awarded published beside any parse), the receiving institution, and its source and substitute courses, each resolved or stated unresolved. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "comparability_id" ], "properties": { "comparability_id": { "type": "string", "description": "A comparability id from find_comparability" } } }arguments 12 linessearch_certifications unknown 29h ago
Which certification is this prose name? Start here for any plain question — a trade, field, job, skill, or company in everyday words. Returns candidates with ids, issuers, and source basis — candidates rather than a single guess when the name is ambiguous; the ids feed the other certification tools.
{ "type": "object", "required": [ "query" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 50)" }, "query": { "type": "string", "examples": [ "nursing", "HVAC", "welding", "IBM", "project management" ], "description": "What you are looking for, in everyday words — a trade, field, job, or company" }, "issuer": { "type": "string", "description": "Optional: only certifications from this organization" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" } } }arguments 31 linesfind_catalogs reads unknown 26h ago
Which published catalog editions are held for this institution? Each catalog's edition year, format and source. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitid" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "description": "The institution's IPEDS UNITID, e.g. 225070" } } }arguments 20 linesfind_policies unknown 22h ago
Which academic policies does this institution publish (transfer credit, prior learning, tuition and fees …)? Optional words narrow them. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
{ "type": "object", "required": [ "unitid" ], "properties": { "limit": { "type": "integer", "description": "Optional page size (default 20, at most 100)" }, "query": { "type": "string", "description": "Optional policy words, e.g. transfer" }, "offset": { "type": "integer", "description": "Optional: the next_offset from a previous answer" }, "unitid": { "type": "string", "description": "The institution's IPEDS UNITID, e.g. 225070" } } }arguments 24 linesassemble_my_formal_education changes data unknown 17h ago
Read a person's transcripts into their evidence package: each file's text and status, its courses and exams as rows, and the items will_my_credits_transfer takes (courses as { unitid or school, code }; AP, CLEP and IB exams with a score). Ask the person for each transcript and the school it came from. Several transcripts are read side by side. A school several schools' names fit is answered with the candidates, and nothing is read. Nothing is stored: the answer returns the package for the agent to keep.
{ "type": "object", "required": [ "files" ], "properties": { "files": { "type": "array", "items": { "type": "object", "required": [ "slot", "filename", "content_base64" ], "properties": { "slot": { "enum": [ "transcript" ], "type": "string" }, "school": { "type": "string", "description": "The school the transcript came from, a name or initials (e.g. CNM); ask the person" }, "unitid": { "type": "string", "description": "Or the school's IPEDS UNITID, e.g. 187532" }, "filename": { "type": "string" }, "content_base64": { "type": "string", "description": "The file's bytes, base64. A call's files total at most about 1.5 MB; send more over several calls with the same package." } } }, "description": "1 or more transcripts" }, "package": { "type": "object", "description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy." } } }arguments 47 linescompare_my_major unknown 14h ago
How do these majors differ? Two to five majors at one level, side by side: definition, the schools offering it, the jobs and their outlook from O*NET, and earnings at 1 and 5 years with debt — given as the LOWEST-TO-HIGHEST RANGE across the schools that publish them, with the number of schools stated. A range of school figures, never a median computed from them. A six-digit major's earnings come from its four-digit series and every such figure is labelled series-level. Every column is complete, or it says which figure is not published.
{ "type": "object", "required": [ "majors", "level" ], "properties": { "level": { "type": "string", "examples": [ "certificate" ], "description": "The credential level to compare at, e.g. certificate" }, "state": { "type": "string", "description": "Optional two-letter state, for the school counts" }, "majors": { "type": "array", "items": { "type": "string" }, "examples": [ [ "CIP:51.3901", "CIP:51.3902" ] ], "description": "2 to 5 majors, each a major_minor_id (e.g. CIP:51.3801) or a CIP code" } } }arguments 33 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idc6957a096d01e462.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/c6957a096d01e462/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/c6957a096d01e462?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.