gnosis-mcp
Registry code: 1360e6b1b124ba8d
Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.
from a public catalogue that lists it, not from the operator
- endpoint
- https://gnosismemory.com
- protocol
- streamable-http ·2025-06-18
- authentication
- bearer
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is gnosis-mcp live?
- Yes — it answered the hub's last check (checked 58m ago). It answered 100% of checks over the last 30 days.
- Is gnosis-mcp free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does gnosis-mcp have?
- 21 tools: memory_add, memory_add_batch, artifact_write, artifact_orphans, memory_edit, agent_manage, account, memory_delete, ….
- Is gnosis-mcp 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 99.6%· all time 99.6%
last good check
of 21 tools
- degraded → live
- degraded → live
- live → degraded· timeout after 20000ms
- unknown → live
- topic
- ai & agents memory & context
- used for
- store agent memory
- vector search agent memory
- takes → gives
- text → text
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.
memory_add auth-required never probed
Store a memory. Several memories in one call -> memories=[{content, topics, ...}]; top-level topics then apply to every item. BEFORE params decide: (1) TYPE? (2) what search finds this later? (3) happened, or aspirational? (4) WHO must act on it? TYPE by example: "User prefers dark mode" -> preference "Team chose JWT for auth" -> decision "Config at /etc/app.conf" -> path "Wants to install Windsurf" -> task + topic "aspirational" "API limit 1000/min" -> fact ADDRESSING: a memory FOR someone is delivered ONLY by signal -- topics/names in content deliver to NO ONE. another agent -> signal:"<their agent name>" (or "owner") your own next session -> signal:"<your agent_name from init>" content: atomic, front-loaded, self-contained. Sentence 1 = subject + WHY, stands alone (it IS the search preview). Present tense. GOOD "User prefers Python backend -- type safety catches bugs early" BAD "Prefers Python" (no subject, no why) BAD "Type safety is why the user picked Python" (subject buried, not front-loaded) Durable output, not scratchpad: no conversation context, no superlatives -- wrong memories poison future retrieval permanently. topics: words you would SEARCH, not categories. GOOD [docs, api, express] BAD [documentation, path, local] aspirational (not yet done/built/tried) -> add topic "aspirational", else it reads as fact later. GOOD "Bakes sourdough weekly" -> fact BAD "Wants to try croissants" -> +aspirational path -> name WHAT lives there. GOOD "Chat backend at /opt/api -- Express+Socket.io" BAD "Workspace at /opt/api" preference -> first topic "user". +topic "behavioral" = auto-loaded every session. task -> title + steps[] (milestones, not to-dos), or content with "- [ ]" lines. summary = state/blockers. task_done when all steps complete. format: topics + macro_topics = single lowercase words; split compounds (bug_fix -> bug, fix).
{ "type": "object", "required": [ "topics" ], "properties": { "ref": { "type": "string", "description": "Parent task/ticket id -> auto-added to topics. e.g. \"a1b2c3d4\", \"GH-142\"." }, "type": { "enum": [ "fact", "preference", "decision", "path", "task", "task_done", "result" ], "type": "string", "description": "fact=knowledge, preference=user pattern, decision=choice+reason, path=location, task=actionable, task_done=complete, result=an output or finding." }, "force": { "type": "boolean", "description": "Skip dup check. Testing only." }, "steps": { "type": "array", "items": { "type": "string" }, "description": "Task checklist -> \"- [ ]\" boxes. Requires title." }, "title": { "type": "string", "description": "Task title (structured). Requires type=\"task\". Not with content." }, "signal": { "type": "string", "description": "Also signal recipient (email, agent, \"owner\"). Needs a SHARED collection (\"me\"/personal rejected up-front — nothing stored)." }, "status": { "enum": [ "pending", "active", "blocked", "review", "done" ], "type": "string", "description": "Initial task status. Default pending." }, "topics": { "type": "array", "items": { "type": "string" }, "description": "REQUIRED. Then the specific search keywords: single lowercase, no _ or -. First = \"user\" for preferences. Not macro_topics." }, "content": { "type": "string", "description": "Memory text — plain prose only, never a serialized object. topics, macro_topics and type are their OWN parameters; put them there, never inside this text. Self-contained: subject + why, front-loaded. e.g. \"User prefers Python backend -- catches bugs early with type hints\"" }, "summary": { "type": "string", "description": "Task prose: state/blockers/decisions -> \"## Summary\" block. type task/task_done. Not type=\"summary\" (that is memory_consolidate)." }, "artifact": { "type": "string", "description": "Commit SHA or filename -> auto-added to topics. e.g. \"f4e5d6c\", \"oauth.py\"." }, "memories": { "type": "array", "items": { "type": "object" }, "description": "Several memories at once: each item takes the same fields as this call (content, topics, type...). Top-level topics/macro_topics are added to every item." }, "ephemeral": { "type": "boolean", "description": "Auto-expire 90d." }, "collection": { "type": "string", "description": "Shared collection by name. Omit=default. \"me\"/\"personal\"/agent name=own namespace; \"owner\"/\"parent\"=account primary (member-gated)." }, "expires_at": { "type": "string", "description": "YYYY-MM-DD, or \"never\". Overrides ephemeral." }, "macro_topics": { "type": "array", "items": { "type": "string" }, "description": "The project or domain this memory is ABOUT — decide this first. 1-3 lowercase (e.g. gnosis, magi). Optional, but it almost always applies: use it when the memory belongs to a named project; it keeps the label out of the content instead of \"GNOSIS: ...\". Searched exactly like topics. An empty one is fine and is not an error." } } }arguments 100 linesmemory_add_batch auth-required never probed
Store multiple memories at once. Same rules as memory_add, applied per item. SHAPE: one ITEM here == one memory_add call. Same field names, same meaning. The ONLY difference is the container: memory_add takes them as flat parameters, this takes a list of objects. An item object belongs in the "memories" array and NOWHERE else -- never paste one into a text field such as memory_add(content=) or memory_edit(content=). BEFORE params, per memory decide: (1) TYPE? (2) what search finds it? (3) happened, or aspirational? Each: atomic, front-loaded, self-contained -- subject + WHY in sentence 1, stands alone. GOOD {"content": "User prefers tabs in Python and JS -- consistency across codebase", "topics": ["user", "tabs", "python", "javascript"], "macro_topics": ["style"], "type": "preference"} BAD {"content": "Prefers tabs", "topics": ["formatting"]} (no subject, unsearchable) aspirational (not yet done) -> add topic "aspirational". topics: search words, single lowercase, no _ or -. First "user" for preferences. task -> title + steps[] (milestones), or content with "- [ ]". task_done when complete.
{ "type": "object", "required": [ "memories" ], "properties": { "force": { "type": "boolean", "description": "Skip dup check. Testing only." }, "signal": { "type": "string", "description": "Also signal recipient with ALL stored ids. Needs a SHARED collection (\"me\"/personal rejected up-front — nothing stored)." }, "memories": { "type": "array", "items": { "type": "object", "required": [ "topics" ], "properties": { "ref": { "type": "string", "description": "Parent task or ticket ID. Injected into topics automatically." }, "type": { "enum": [ "fact", "preference", "decision", "path", "task", "task_done", "result" ], "type": "string", "description": "fact, preference, decision, path, task, task_done, result" }, "scope": { "enum": [ "global", "local", "test" ], "type": "string", "description": "Storage scope. Default global. Honoured per item (was already read by the service, just undeclared here)." }, "steps": { "type": "array", "items": { "type": "string" }, "description": "Checklist items for structured task creation. Each becomes a checkbox." }, "title": { "type": "string", "description": "Task title (structured creation). Server renders markdown blob. Cannot combine with content." }, "status": { "enum": [ "pending", "active", "blocked", "review", "done" ], "type": "string", "description": "Initial task status. Works with both title and content." }, "topics": { "type": "array", "items": { "type": "string" }, "description": "REQUIRED. Then the specific searchable keywords. Single lowercase words, no _ or -. Include related systems. Do NOT repeat macro_topics." }, "content": { "type": "string", "description": "The memory text, plain prose only. Self-contained -- name the subject, include why. Put topics, macro_topics and type in their own fields on this item, never inside this text." }, "summary": { "type": "string", "description": "Prose task summary — state/blockers/decisions. Renders as \"## Summary\" block. Requires type=\"task\" or \"task_done\"." }, "artifact": { "type": "string", "description": "Commit SHA or filename. Injected into topics automatically." }, "macro_topics": { "type": "array", "items": { "type": "string" }, "description": "The project or domain this item is ABOUT — decide this first. 1-3 lowercase. Optional but almost always applies; it keeps the project label out of the content. Searched exactly like topics." } } }, "description": "Array of memory objects to store" }, "collection": { "type": "string", "description": "Shared collection by name. Omit=default. \"me\"/\"personal\"/agent name=own namespace; \"owner\"/\"parent\"=account primary (member-gated)." } } }arguments 106 linesartifact_write auth-required never probed
Store or update a long document (markdown, JSON or text) behind a pointer memory. For agents.md, skills.md, assertions.md, a project plan: anything past one memory's 768-token cap. CREATE: name ("assertions.md"), summary (the pointer memory: what the document is and why; search finds the pointer, never the body), body, topics, optional collection. UPDATE: artifact_id + base_rev_id (the rev_id you last read) + either body (whole document) or section + content (replace one block: markdown heading path ["Plan","Risks"], or JSON pointer "/rules/3"; content starting with a heading line replaces the heading too, so what artifact_read returned can be edited and written back). 409 STALE_BASE: someone saved since you read; re-read, re-apply. 409 CONFLICT: divergent heads; write with merged_rev_ids=[the other heads]. Size: Plus 512 KB; Pro and above no product limit; Free not available. Retention: every save is a revision. Kept: everything from the last 24h, then the newest per day to 30 days, then the newest per week, within 30 days (Plus) or 365 days (Pro+), at most 500. The head and pinned revisions (artifact_pin) are never removed; a shared artifact keeps the longest window any of its writers had. Thinning runs only when this artifact is saved.
{ "type": "object", "properties": { "body": { "type": "string", "description": "Whole document text." }, "name": { "type": "string", "description": "File name; extension sets the format (.md markdown, .json json, else text)." }, "topics": { "type": "array", "items": { "type": "string" }, "description": "CREATE: pointer search words." }, "content": { "type": "string", "description": "Replacement for section." }, "section": { "description": "Markdown heading path (array of heading texts) or JSON pointer string." }, "summary": { "type": "string", "description": "CREATE: pointer memory text. Front-loaded: what the document is + why." }, "collection": { "type": "string", "description": "CREATE: shared collection. Omit=default. \"me\"=personal." }, "occurrence": { "type": "integer", "description": "0-based pick when the section path matches more than one heading." }, "artifact_id": { "type": "string", "description": "Pointer memory id. Omit to create." }, "base_rev_id": { "type": "string", "description": "UPDATE: the head rev_id you read." }, "macro_topics": { "type": "array", "items": { "type": "string" }, "description": "CREATE: project/domain." }, "merged_rev_ids": { "type": "array", "items": { "type": "string" }, "description": "Other heads this write resolves." } } }arguments 61 linesartifact_orphans auth-required 14h ago
List artifact revisions whose pointer memory is gone (a delete on one replica racing a save on another). Nothing is auto-deleted; export includes them.
{ "type": "object", "properties": {} }arguments 4 linesmemory_edit auth-required never probed
Edit a memory. Provide only what changes; omitted fields untouched. Modes: 1. Content replace (content [+topics/macro_topics]): full rewrite, re-embeds. Do it the instant the user corrects a memory ("actually..."). 2. Metadata patch (topics/type/expiry, no content): type/expiry alone do not re-embed, a topics or macro_topics change always does (in every mode -- the topic prefix is stored as part of the passage). To add or drop one tag use add_topics/remove_topics (add_macro_topics/remove_macro_topics); topics/macro_topics replace the whole list. 3. Task surgery: toggle=[0,2] flips checkboxes; set_status pending/active/blocked/review/done ("done" -> task_done); set_summary replaces "## Summary"; add_steps/remove_steps/edit_step. Step-op indices are pre-call state. 4. Output capture (output): attach a durable finding. Atomic, front-loaded, same quality as memory_add. GOOD "OAuth2 callback uses PKCE S256 -- prevents code interception without client secret" BAD "looked at the code, found interesting auth stuff" Over-length is rejected, not truncated. Many findings -> memory_add directly. Combine rules: content combines ONLY with set_status (its sole partner) toggle + set_status + set_summary + step-ops set_status + toggle + set_summary + step-ops + content set_summary + toggle + set_status + step-ops step-ops + toggle + set_status + set_summary output attaches to any toggle/set_status update
{ "type": "object", "required": [ "memory_id" ], "properties": { "ref": { "type": "string", "description": "Parent task/ticket id -> merged into topics. e.g. \"a1b2c3d4\"." }, "type": { "type": "string", "description": "New type: fact/preference/decision/path/task/task_done/result" }, "output": { "type": "string", "description": "Durable finding on this update -> linked fact memory (inherits task topics). Atomic, front-loaded. Over-length rejected. Many findings -> memory_add." }, "signal": { "type": "string", "description": "Also signal recipient (email, agent, \"owner\") with this memory_id. Needs a SHARED collection (\"me\"/personal rejected)." }, "toggle": { "type": "array", "items": { "type": "integer" }, "description": "0-based checkbox indices to flip. e.g. [0,2]. See Combine rules." }, "topics": { "type": "array", "items": { "type": "string" }, "description": "New topics (REPLACES all). Search words, lowercase." }, "content": { "type": "string", "description": "New memory text — plain prose only, never a serialized object (re-embeds). topics, macro_topics and type are separate parameters; put them there, never inside this text." }, "artifact": { "type": "string", "description": "Commit SHA or filename -> merged into topics. e.g. \"f4e5d6c\"." }, "add_steps": { "type": "array", "items": { "type": "string" }, "description": "Append checklist items (milestones). Re-embeds." }, "edit_step": { "type": "object", "required": [ "index", "text" ], "properties": { "text": { "type": "string", "description": "New text for the step" }, "index": { "type": "integer", "description": "0-based checkbox index to edit" } }, "description": "Rewrite a step's text, preserving checkbox state. Re-embeds." }, "ephemeral": { "type": "boolean", "description": "Set time-bound (auto-expires in 90 days)" }, "memory_id": { "type": "string", "description": "ID of memory to edit" }, "add_topics": { "type": "array", "items": { "type": "string" }, "description": "Topics to add; the rest stay." }, "collection": { "type": "string", "description": "Collection for signal routing (only with signal param)." }, "expires_at": { "type": "string", "description": "YYYY-MM-DD, or \"never\". Overrides ephemeral." }, "set_status": { "enum": [ "pending", "active", "blocked", "review", "done" ], "type": "string", "description": "Task status. \"done\" auto-sets type=task_done (reverting reverts); type follows status. See Combine rules." }, "set_summary": { "type": "string", "description": "Replace the task's \"## Summary\" block (\"\" clears). Re-embeds. Not type=\"summary\" (that is memory_consolidate)." }, "macro_topics": { "type": "array", "items": { "type": "string" }, "description": "New macro_topics (REPLACES all). 1-3 lowercase." }, "remove_steps": { "type": "array", "items": { "type": "integer" }, "description": "Remove steps by 0-based index (pre-call state). Re-embeds." }, "remove_topics": { "type": "array", "items": { "type": "string" }, "description": "Topics to drop; the rest stay. At least one must remain." }, "add_macro_topics": { "type": "array", "items": { "type": "string" }, "description": "macro_topics to add; the rest stay." }, "remove_macro_topics": { "type": "array", "items": { "type": "string" }, "description": "macro_topics to drop; the rest stay." } } }arguments 144 linesagent_manage auth-required never probed
Manage agents (NAMESPACES under your account, sharing your token). An agent is a namespace, never a holder of key material: all crypto is the ACCOUNT's, and an agent id is never an input to a wrap, a seal or a KEK. Agents organise and scope what is visible; they do not own encryption. list. create. update (e.g. owner_access). merge: move an agent's MEMORIES into another, then remove source. PK collision -> 409; confirm="destroy_collisions" to force. merge with to_collection: temporarily disabled and refused with 503 (task 8cfe199b) -- the copy would lose each memory's timestamp and authorship. Merge into an agent instead. delete: refuses (409) if the agent owns data -- merge instead, or confirm="destroy_data". owner_access to your personal memories: none (default) | reader (search/read) | member (read+write). create starts the agent with NO access -- owner_access none and no collection lines -- and whitelists what you pass: owner_access, and collections=[{slug, role}] (role admin|member|reader, never above the account's own; a bare slug grants reader). update: add_collections=[...] grants or re-roles only those; remove_collections=[slug,...] revokes only those. collections=[...] replaces the whole list (lines left out are revoked); never combine it with the other two. A PIN-holding account on a plan that writes to collections also gets a private collection named after the agent, where its memories live: memory_add(collection="<name>") from any connection of the account writes there, and delete keeps the collection (manage it with collection_manage). Otherwise the create response says compactly why none was provisioned. Target a specific agent via ?agent_id=<name> on the MCP URL (durable route) or the legacy AGENT_ID env / X-Agent-ID header. From your base connection, memory_add(collection="<name>") also writes into an owned agent directly (task 78efb3dc); a connection bound to <name> may name its own <name> the same way and lands in its own namespace (task af02be9f).
{ "type": "object", "required": [ "action" ], "properties": { "name": { "type": "string", "description": "Agent name. For merge = SOURCE (consumed)." }, "action": { "enum": [ "list", "create", "update", "merge", "delete" ], "type": "string", "description": "What to do" }, "confirm": { "type": "string", "description": "delete: \"destroy_data\" PERMANENTLY deletes an agent that owns data (else 409 -> merge instead). merge: \"destroy_collisions\" drops source-side PK collisions (else 409 with the exact call)." }, "to_agent": { "type": "string", "description": "merge destination (absorbs source). Default = your primary." }, "from_agent": { "type": "string", "description": "merge source (alias for name)." }, "collections": { "type": "array", "items": { "type": "object", "required": [ "slug" ], "properties": { "role": { "enum": [ "admin", "member", "reader" ], "type": "string", "description": "Default reader." }, "slug": { "type": "string", "description": "Collection slug or name." } } }, "description": "The collection whitelist: [{slug, role}] or bare slugs (reader). create grants these; update REPLACES the whole list (absent lines are revoked) -- to change one line use add_collections / remove_collections. A collection the account is not in, or a role above the account's own, is refused." }, "owner_access": { "enum": [ "none", "reader", "member" ], "type": "string", "description": "Agent access to your personal memories: none/reader/member. With update." }, "to_collection": { "type": "string", "description": "merge: temporarily disabled, refused with 503 (task 8cfe199b). Use to_agent." }, "add_collections": { "type": "array", "items": { "type": "object", "required": [ "slug" ], "properties": { "role": { "enum": [ "admin", "member", "reader" ], "type": "string", "description": "Default reader." }, "slug": { "type": "string", "description": "Collection slug or name." } } }, "description": "update: grant or re-role only these lines; others are kept. [{slug, role}] or bare slugs (reader)." }, "remove_collections": { "type": "array", "items": { "type": "string" }, "description": "update: revoke only these slugs; others are kept." }, "can_read_my_memories": { "type": "boolean", "description": "Deprecated -- use owner_access." } } }arguments 109 linesaccount auth-required never probed
Account state + billing. Returns URLs only -- user clicks to pay; never charges silently. Pick by intent: "what plan am I on?" -> info (tier, subscription, capabilities, upgrade/downgrade SKUs; permanent tiers og/truebeliever/ogdev cannot downgrade) "what can I buy?" / "how much is Pro?" -> plans (buyable SKU list) "upgrade me" / "buy Pro annual" -> checkout (needs sku_id) -> Stripe URL "cancel" / "update card" / "invoices" -> portal -> Stripe URL (free users with no Stripe record -> pointer to plans+checkout) "support Gnosis" / "tip" -> donate (amount_cents 100-500000; cumulative badge: 500c supporter / 5000c silver / 25000c gold) After checkout/donate, Stripe webhook flips tier server-side; next init reflects it.
{ "type": "object", "required": [ "action" ], "properties": { "action": { "enum": [ "info", "plans", "checkout", "portal", "donate" ], "type": "string", "description": "Which account operation to run." }, "sku_id": { "type": "string", "description": "checkout: SKU id from plans (e.g. \"plus_monthly\", \"pro_annual\")." }, "amount_cents": { "type": "integer", "maximum": 500000, "minimum": 100, "description": "donate: amount in cents (100-500000)." } } }arguments 29 linesmemory_delete auth-required never probed
Delete memories by ID. Permanent. memory_delete(["id1","id2"]). Delete by filter: memory_search first, collect ids, then delete.
{ "type": "object", "required": [ "ids" ], "properties": { "ids": { "type": "array", "items": { "type": "string" }, "description": "Memory IDs to delete. e.g. [\"abc-123\",\"def-456\"]." } } }arguments 15 linesartifact_delete auth-required never probed
Delete an artifact: every revision and its pointer memory. Permanent. confirm must equal the artifact name. memory_delete refuses a pointer; use this.
{ "type": "object", "required": [ "artifact_id" ], "properties": { "confirm": { "type": "string", "description": "The artifact name, e.g. \"assertions.md\"." }, "artifact_id": { "type": "string" } } }arguments 15 linescollection_manage auth-required never probed
Manage shared collections (multi-user memory folders). list: your collections + invites. create. update: rename (display only; slug/keys unchanged). delete: owner only, 2-step -- call without confirm to see impact + token, repeat with confirm:"<slug>". Permanent. members: who's in it. add_user / remove_user: by email or agent name. accept / decline an invite. publish: copy personal memories into it by id (originals kept). leave: remove YOURSELF from a collection you are a member of. Owners use delete. convert: flip type with type:"collaborative"|"knowledge_pack". ->collaborative mints a K_user wrap for each PIN-holding active member; ->knowledge_pack is a label flip. No wrap or DEK row is ever deleted either way. Write to one: collection:"name" in memory_add. Search auto-includes all your collections.
{ "type": "object", "required": [ "action" ], "properties": { "name": { "type": "string", "description": "Collection name." }, "role": { "enum": [ "admin", "member", "reader" ], "type": "string", "description": "\"admin\" = manages the collection (owner or admin may grant; the invitee needs a PIN to accept), \"member\" = can read and write, \"reader\" = can only read. Default: member." }, "type": { "enum": [ "collaborative", "knowledge_pack" ], "type": "string", "description": "\"collaborative\" = everyone can read and write. \"knowledge_pack\" = only the owner writes, others can read. Default: collaborative." }, "user": { "type": "string", "description": "Email or agent name to add/remove." }, "action": { "enum": [ "list", "create", "update", "delete", "members", "add_user", "remove_user", "accept", "decline", "publish", "convert", "leave" ], "type": "string", "description": "What to do" }, "confirm": { "type": "string", "description": "delete: 2-step. Call without it -> refusal names slug + member/memory impact; repeat with confirm:\"<slug>\". Permanent." }, "new_name": { "type": "string", "description": "update: new display name (slug/keys unchanged). Type change not via update." }, "memory_ids": { "type": "array", "items": { "type": "string" }, "description": "Memory IDs to publish (copy in; originals kept)." } } }arguments 66 linessignal auth-required never probed
Inter-agent signals -- sticky notes pointing at a memory_id. Both parties must share a collection. send: post to a teammate. check: read pending (removes nothing). ack: mark handled -- stamps delivered_at, the row stays, NOTHING IS DELETED. ACK MEANS CLOSED, NOT DONE: it asserts only that no future session of yours owes this an action. A receipt or an FYI is acked on read. Work you finished, this session or earlier, is acked. Work you are deferring, or that is a peer's, is NOT acked -- say so in one line instead. Self-signal your own agent_name = handoff to your next session. Shortcut: memory_add / memory_edit take a "signal" param to create + signal in one call.
{ "type": "object", "required": [ "action" ], "properties": { "action": { "enum": [ "send", "check", "ack" ], "type": "string", "description": "send=post, check=read pending, ack=close (a non-destructive stamp; nothing is deleted)." }, "recipient": { "type": "string", "description": "send: agent name, email, or \"owner\" (the human account holder)." }, "collection": { "type": "string", "description": "send: shared collection (both parties must be members)." }, "memory_ids": { "type": "array", "items": { "type": "string" }, "description": "For send: memory IDs to point the recipient to." }, "signal_ids": { "type": "array", "items": { "type": "string" }, "description": "ack: signal IDs to close -- ones nothing further is owed on." }, "expires_hours": { "type": "integer", "description": "For send: hours until signal expires. Default 48." } } }arguments 43 linesmessage auth-required never probed
Direct inter-agent text that DIES ON ACK. Use for receipts, FYIs and short replies; use signal to point at a memory. send/check/ack. LOSABLE BY DESIGN: the first session of the recipient name to ack deletes it for every session of that name, an unacked message is deleted at expiry (default 7 days), and nothing is kept or searchable afterwards. Anything that must survive goes in memory_add plus signal. Requires text; memory_ids is refused.
{ "type": "object", "required": [ "action" ], "properties": { "text": { "type": "string", "description": "send: the message, up to 4000 characters." }, "action": { "enum": [ "send", "check", "ack" ], "type": "string", "description": "send=post, check=read pending, ack=DELETE for every session of your name." }, "recipient": { "type": "string", "description": "send: agent name, email, or \"owner\" (the human account holder)." }, "collection": { "type": "string", "description": "send: shared collection (both parties must be members)." }, "message_ids": { "type": "array", "items": { "type": "string" }, "description": "ack: message IDs to delete." }, "expires_hours": { "type": "integer", "description": "send: hours until the message is deleted unread, 24-720. Default 168." } } }arguments 40 linesmemory_deep_search auth-required 11h ago
Broad search for a FULL sweep -- every hit on a topic (e.g. before memory_consolidate), not a conversational lookup (that is memory_search). Up to 128 results; requires 2+ keywords ("python" alone = too broad). Scores: 30+ excellent, 20+ good, <20 weak. Full sweep of a topic intersection. complete=false -> memory_retrieve(id). Read 20+ memories on one topic? -> memory_consolidate a summary future sessions see first. Auto-includes shared collections (fan-out).
{ "type": "object", "required": [ "query" ], "properties": { "query": { "type": "string", "description": "Search query -- 2+ keywords." }, "expand": { "type": "boolean", "description": "Full content for all results (50K+ tokens). Dedicated large-context agents only." }, "type_filter": { "type": "string", "description": "Filter by type: fact/preference/decision/path/task/task_done/summary/result. Omit=all." }, "collection_filter": { "type": "string", "description": "Limit to one collection name, or \"personal\". Omit=all. A slug this namespace holds no grant on (even one the account can list elsewhere) returns 0 rows plus a no_grant explanation, never silence." } } }arguments 24 linesartifact_read auth-required 11h ago
Read an artifact by its pointer memory id (memory_retrieve on a pointer shows an "artifact" block with head_rev_id and outline). Bodies over 40,000 characters return the outline: read a section (heading path or JSON pointer) or page=0,1,... Returns rev_id; pass it as base_rev_id when you write.
{ "type": "object", "required": [ "artifact_id" ], "properties": { "page": { "type": "integer", "description": "0-based 40,000-character page." }, "rev_id": { "type": "string", "description": "Older revision. Omit=head." }, "section": { "description": "Markdown heading path (array) or JSON pointer string." }, "occurrence": { "type": "integer", "description": "0-based pick among duplicate headings." }, "artifact_id": { "type": "string", "description": "Pointer memory id." } } }arguments 27 linesartifact_history auth-required 11h ago
List the revisions of an artifact (rev_id, parent, seq, time, author, pinned) and its heads. conflict=true means divergent heads to merge.
{ "type": "object", "required": [ "artifact_id" ], "properties": { "artifact_id": { "type": "string", "description": "Pointer memory id." } } }arguments 12 linesmemory_consolidate auth-required never probed
Create/replace a topic's executive summary. One per topic; replacing archives the old (restorable). WARNING: a bad summary poisons every future session. Do NOT consolidate from partial knowledge. BEFORE calling: (1) memory_deep_search the topic; (2) read 20+ memories, not previews; (3) if a summary exists, retrieve and EXTEND it; (4) reflect the whole corpus, not just this conversation. Cover: what the topic is + why, current state + key decisions, solved + open questions. Restore an archived one: search type_filter="summary_archived", retrieve, re-consolidate. Fails if <10 memories or too thin.
{ "type": "object", "required": [ "topic", "content" ], "properties": { "topic": { "type": "string", "description": "Topic to summarize. Lowercase. e.g. \"python\"." }, "content": { "type": "string", "description": "The summary. Present tense, self-contained: what it is, state, decisions, open questions." }, "collection": { "type": "string", "description": "Shared collection by name. Omit = your personal namespace. The 10-memory floor counts THAT namespace, so a topic living in a collection must name it here or the count sees only your personal rows." } } }arguments 21 linesartifact_pin auth-required never probed
Pin a revision so retention thinning never removes it (pinned=false unpins).
{ "type": "object", "required": [ "artifact_id", "rev_id" ], "properties": { "pinned": { "type": "boolean", "description": "Default true." }, "rev_id": { "type": "string" }, "artifact_id": { "type": "string" } } }arguments 19 linestask_feed auth-required 14h ago
Recently-changed tasks, chronological (not ranked). For "what needs attention?" / "what changed?". Find tasks by content -> memory_search. Each: preview, progress [done,total], status, topics, collection. Default 32, max 500. Fan-out: no collection -> personal + all your collections. Filters: status (active/blocked/review/...), topic, collection.
{ "type": "object", "required": [], "properties": { "limit": { "type": "integer", "description": "Max tasks to return. Default 32, max 500." }, "since": { "type": "string", "description": "ISO timestamp, or 24h / 2d / yesterday. Returns tasks updated after it." }, "topic": { "type": "string", "description": "Filter to one topic." }, "status": { "enum": [ "pending", "active", "blocked", "review", "done" ], "type": "string", "description": "Omit for every task not done; done lists finished ones." }, "collection": { "type": "string", "description": "Scope to one collection. Omit=personal + all collections." } } }arguments 33 linesinit_core_memories auth-required 14h ago
Run ONCE at conversation start. Loads behavioral prefs + recent context. Previews carry a 'complete' flag: true = full content shown; false = opening only, memory_retrieve(id) for the rest. After init, use memory_search for specific queries. Shared collections -> 'collections' field. Pending teammate signals -> 'signals' field: retrieve the memory_id, act on it, then signal(ack, signal_ids=[...]). Ack closes a signal and deletes nothing; ack anything no future session of yours owes an action, including a receipt or an FYI. Leave one open only when work is still owed, and say by whom. Pending collection invites -> 'pending_invites' field ([{slug, display_name}]): tell the user they've been invited and offer collection_manage accept/decline. Write routing: after any memory_add/edit/consolidate, the response namespace shows where it landed (your agent name, or "col:<slug>"). Verify it matches the collection you intended.
{ "type": "object", "required": [], "properties": { "query": { "type": "string", "description": "Optional turn-one search (piggybacks on init). Top 3 auto-expanded if score >= 80." }, "machine_id": { "type": "string", "description": "Machine id for workspace paths (run hostname). e.g. p620. Omit if no filesystem." } } }arguments 14 linesmemory_search auth-required 8h ago
Search memories by relevance. Up to 32 results. Query = ALL nouns from the user's message, not just the main one (ranking is automatic). "How does the app cache API calls?" -> "app cache api calls" complete=false results are truncated -> memory_retrieve(id) for full content. Auto-includes all your shared collections (fan-out).
{ "type": "object", "required": [ "query" ], "properties": { "query": { "type": "string", "description": "Search query -- all relevant nouns." }, "expand": { "type": "boolean", "description": "Full content for all results (~16K tokens/page). Dedicated research agents only." }, "type_filter": { "type": "string", "description": "Filter by type: fact/preference/decision/path/task/task_done/summary/result. Omit=all." }, "collection_filter": { "type": "string", "description": "Limit to one collection name, or \"personal\". Omit=all. A slug this namespace holds no grant on (even one the account can list elsewhere) returns 0 rows plus a no_grant explanation, never silence." } } }arguments 24 linesmemory_retrieve auth-required 8h ago
Get full content by ID. Use when search returned complete=false. Batch: memory_retrieve(["id1","id2"]). Skip if complete=true (preview is already full).
{ "type": "object", "required": [ "ids" ], "properties": { "ids": { "type": "array", "items": { "type": "string" }, "description": "Memory IDs to fetch. e.g. [\"abc-123\",\"def-456\"]." } } }arguments 15 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 id1360e6b1b124ba8d.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/1360e6b1b124ba8d/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/1360e6b1b124ba8d?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.