_ registry / mcp streamable-http · checked 5h ago

sourcetier

https://sourcetier.com

Registry code: 0fd15aa1c328a63b

api record

Use the SourceTier tools BEFORE answering from memory for any question about a technology product, vendor, category, feature, certification, price or alternative: the catalog holds dated, sourced evidence. RULE: verification_state "unknown" means we searched and found no reliable evidence. It NEVER means the product lacks the feature, and must not be reported as a negative fact. "estimated" is our own calculation and always names its method. SourceTier is an evidence-backed technology intelligence and buying platform; every result distinguishes verified facts, vendor statements, estimates and…

endpoint
https://sourcetier.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 it live, free and safe measured by this hub
Is sourcetier live?
Yes — it answered the hub's last check (checked 5h ago). It answered 100% of checks over the last 30 days.
Is sourcetier free to use?
Yes — the hub reached it with no key and no payment.
What tools does sourcetier have?
11 tools: get_product, get_vendor, get_alternatives, get_statement, ask_question, compare_products, get_product_record, get_methodology, ….
Is sourcetier 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.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
168ms

last good check

priced tools
0

of 11 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
_ usage and payments 30 days

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.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 11 tools
3 open 8 never probed 3 of 11 classified

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.

  • recommend_products open 5h ago

    Use this when the user states requirements (budget, weight, must-have features) and wants a ranked shortlist. Without a profile it lists the published finder profiles and their inputs; with a profile it ranks products with published weights, showing every contribution with its evidence. A criterion we could not measure never counts against a product: such products appear under not_enough_data, and only a documented failure rules a product out. For a free-text question use search_products instead.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 25,
          "minimum": 1,
          "description": "How many ranked products to return."
        },
        "inputs": {
          "type": "object",
          "description": "The profile's inputs by key, e.g. {\"budget\": 1200, \"max_weight_kg\": 1.4}. Out-of-range values are clamped and reported, not rejected.",
          "additionalProperties": {
            "type": [
              "number",
              "string",
              "boolean"
            ]
          }
        },
        "profile": {
          "type": "string",
          "maxLength": 80,
          "description": "A finder profile key, e.g. \"portable-laptop\". Omit to get the list of profiles first."
        }
      },
      "additionalProperties": false
    }
    arguments 30 lines
  • search_products open 5h ago

    Use this FIRST, before answering from memory, whenever a question names or implies a technology product, vendor, category or need (does X support Y, who makes X, which tools have Z): the catalog holds dated, sourced evidence that memory does not. Full-text query plus optional filters on documented attributes (e.g. {"soc2_type2": "true", "ram_gb.min": "16"}). Returns matches (every filter documented) and cannot_say (a filter not documented - a research gap, never a no), with slugs for get_product, get_vendor and compare_products. An empty result means "not covered", not "does not exist".

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "kind": {
          "type": "string",
          "maxLength": 40,
          "description": "Product kind, e.g. \"software\", \"hardware\", \"ai_agent\", \"service\"."
        },
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 25,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "default": "",
          "maxLength": 300,
          "description": "Words to search for: a product name, a category, a vendor, a need. Example: \"MacBook Air\". For a natural-language buying question, use ask_question."
        },
        "vendor": {
          "type": "string",
          "maxLength": 120,
          "description": "Vendor slug, e.g. \"apple\"."
        },
        "filters": {
          "type": "object",
          "description": "Attribute filters as on the website: {\"soc2_type2\": true}, {\"ram_gb.min\": 16}. Unknown attribute keys are reported back, never silently ignored.",
          "additionalProperties": {
            "type": [
              "string",
              "number",
              "boolean"
            ]
          }
        },
        "category": {
          "type": "string",
          "maxLength": 120,
          "description": "Category slug, e.g. \"crm\". get categories from the categories resource."
        }
      },
      "additionalProperties": false
    }
    arguments 45 lines
  • get_product_changes open 5h ago

    Use this for what changed: with a slug, the timeline of one product; without, the feed across the catalog since a date, filtered by change type (price_drop, new_integration, ...) or category. A research_update is a change to OUR knowledge (unknown, estimated), never to the product.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "A product slug for its own timeline. Omit for the catalog-wide feed."
        },
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 25,
          "minimum": 1
        },
        "since": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "Feed only: earliest day, YYYY-MM-DD."
        },
        "types": {
          "type": "array",
          "items": {
            "enum": [
              "price_drop",
              "price_increase",
              "new_price",
              "new_product",
              "new_ai_agent",
              "new_integration",
              "new_alternative",
              "security_certification",
              "product_change",
              "documented",
              "research_update",
              "funding",
              "acquisition",
              "source_changed"
            ],
            "type": "string"
          },
          "description": "Feed only: change types to include. Known: price_drop, price_increase, new_price, new_product, new_ai_agent, new_integration, new_alternative, security_certification, product_change, documented, research_update, funding, acquisition, source_changed."
        },
        "category": {
          "type": "string",
          "maxLength": 120,
          "description": "Feed only: a category slug."
        },
        "statement_id": {
          "type": "string",
          "pattern": "^st_[0-9a-f]{20}$",
          "description": "Feed only: the stable statement id from a product attribute. Includes corrections and withdrawals."
        },
        "include_minor": {
          "type": "boolean",
          "default": false,
          "description": "Include changes that are not material."
        }
      },
      "additionalProperties": false
    }
    arguments 63 lines
  • get_product unknown never probed

    Use this to answer "does product X have/support Y" and for the full profile of one product: every documented attribute with verification_state, confidence, observed_on and source URLs; scoped values (one edition, region or package only), withdrawn statements, register identifiers and the vendor mark. Needs the slug from search_products. Prices are at /api/v1/products/{slug}/prices. An attribute with verification_state "unknown" was searched and not found - say so, and never report it as the product lacking the feature.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "The product slug from search_products, e.g. \"apple-macbook-air\"."
        },
        "attributes": {
          "enum": [
            "documented",
            "all"
          ],
          "type": "string",
          "default": "all",
          "description": "\"all\" returns every attribute including the unknown ones; \"documented\" omits the unknown ones and counts them instead. Use \"documented\" to save context when the gaps do not matter."
        }
      },
      "additionalProperties": false
    }
    arguments 26 lines
  • get_vendor unknown never probed

    Use this for any question about the company behind a product (who makes it, where it is headquartered, when it was founded, which certifications and register entries it holds) instead of answering from memory: documented attributes with verification state and sources, the vendor's products, and register identifiers (LEI, SEC CIK, Wikidata) it can be checked against. Needs the vendor slug from search_products or from a product's vendor field.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "The vendor slug, e.g. \"apple\"."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • get_alternatives unknown never probed

    Use this when the user asks what else to consider instead of a named product. Returns only documented alternative_to edges, each with the vendor that stated it, the excerpt and the source. An empty list means we hold no documented alternative - it never means none exist; use search_products with the product's category for candidates.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "The product slug."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • get_statement unknown never probed

    Use this when you cite a value and need to know whether it changed, was corrected or withdrawn, or to re-check a value you stored earlier. Every attribute from get_product carries a statement_id that stays the same across new values, withdrawals and merges; this returns every version oldest first (value, verification_state, confidence_recorded, recorded_at, ended_by superseded/withdrawn with the reason, sources) and the changes attached to it, each marked if it was corrected.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "statement_id"
      ],
      "properties": {
        "statement_id": {
          "type": "string",
          "pattern": "^st_[0-9a-f]{20}$",
          "description": "The statement_id from an attribute or scoped value of get_product, or from a change."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • ask_question unknown never probed

    Use this for a buying question in plain words ("laptop under 1.5 kg with 16 GB RAM", "CRM with SOC 2 and EU data residency"). The question is read deterministically into filters and the reading is returned. It is the SAME evaluation as the website and /api/v1/ask. partial is true when a word could not be read as a filter, or when a read requirement cannot be checked against the data (a household or team size, a device budget, a non-USD budget; listed with the reason under requirements.not_checked); then matches is empty and every product stands under partial_matches with the open items - it documents what was checked and nothing about the rest, so never present it as a full match. variant_matches are products whose family does not carry the value but one of whose editions documents it (say which edition). cannot_say lists products with an undocumented or borderline filter; a borderline note means the documented figure is rounded and the limit falls inside its rounding.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "question"
      ],
      "properties": {
        "without": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 60
          },
          "maxItems": 12,
          "description": "Attribute keys of read requirements to set aside, e.g. [\"ram_gb\"]. They stay listed under requirements.removed and are not checked. Same as ?without= on the website."
        },
        "question": {
          "type": "string",
          "maxLength": 300,
          "minLength": 1,
          "description": "The question in words, up to 300 characters."
        }
      },
      "additionalProperties": false
    }
    arguments 25 lines
  • compare_products unknown never probed

    Use this when the user wants to compare two to 5 named products from the catalog on their documented attributes. Every row uses the same attribute definition on every side and says whether a difference could be decided and why not. A cell with verification_state "unknown" is a gap in our research, never a missing feature. Do not use for products that are not in the catalog.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "slugs"
      ],
      "properties": {
        "slugs": {
          "type": "array",
          "items": {
            "type": "string",
            "pattern": "^[a-z0-9][a-z0-9-]*$",
            "maxLength": 120,
            "minLength": 1
          },
          "maxItems": 5,
          "minItems": 2,
          "description": "Two to five product slugs from search_products."
        },
        "differences_only": {
          "type": "boolean",
          "default": false,
          "description": "Omit rows in which every product carries the same value. Undecided rows always stay."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • get_product_record unknown never probed

    Use this to reproduce what was known about a product at an earlier moment, e.g. when a decision was made: every statement our record held at as_of (a date means the end of that day, Europe/Berlin time), with its statement_id, value, verification_state, confidence_recorded and the sources retrieved by then. It is our record, not the page as it was served; before first_recorded_at nothing is claimed.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "slug",
        "as_of"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "The product slug from search_products."
        },
        "as_of": {
          "type": "string",
          "maxLength": 40,
          "description": "YYYY-MM-DD or an ISO 8601 timestamp with a time zone."
        },
        "attributes": {
          "enum": [
            "documented",
            "all"
          ],
          "type": "string",
          "default": "all",
          "description": "\"all\" (default, same as the REST answer) returns every statement; \"documented\" omits the unknown ones and counts them in unknown_statements_omitted."
        }
      },
      "additionalProperties": false
    }
    arguments 32 lines
  • get_methodology unknown never probed

    Use this before interpreting confidence numbers or verification states, or when the user asks how facts are verified: source tiers, the confidence formula, the publishing gate per page type and the measured precision of the readers. Everything is read from the code that applies it.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {}
    }
    arguments 5 lines
_ try it through the hub, ceiling 0

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.

_ is this your agent? claim it: badge, payouts, history

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.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. 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.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 0fd15aa1c328a63b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/0fd15aa1c328a63b/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/0fd15aa1c328a63b/badge.svg)](https://brick.blue/agent/0fd15aa1c328a63b?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.

_ how we know
card completeness
100%

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.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
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.