Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Gnosis Memory

REMOTE · GNOSISMEMORY.COM

Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.

Available components

+3 this week 81 Trust /100

Last scanned (22 hours ago)

Scores higher than 79% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Memory and Knowledge

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability57
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 6354 tokens (~302/item across 21 items; 21 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
  • Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 97% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://gnosismemory.com

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=gnosismemory.com CN=WE1,O=Google Trust Services,C=US 25 Sept 2026 24 Dec 2026 ECDSA 256 ECDSA-SHA256 87e994417dd8c0270eb8f1f5a9be9c72
SANs: gnosismemory.com, *.gnosismemory.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of gnosismemory.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
gnosismemory.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="OAuth", error="invalid_token", error_description="Missing or invalid access token", resource_metadata="https://gnosismemory.com/.well-known/oauth-protected-resource/"

Bearer realm="OAuth", error="invalid_token", error_description="Missing or invalid access token", resource_metadata="https://gnosismemory.com/.well-known/oauth-protected-resource/"
Header Value
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net; style-src 'self' 'unsafe-inline'; img-src 'self' data: https://*.googleusercontent.com; connect-src 'self'; frame-ancestors 'none'; base-uri 'self'; form-action 'self'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

Protected resource metadata

Document https://gnosismemory.com/.well-known/oauth-protected-resource/
Retrieved Yes
Resource https://gnosismemory.com/
Authorisation server https://gnosismemory.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://gnosismemory.com Verified 200
http (plaintext) http://gnosismemory.com HTTPS enforced 301 https://gnosismemory.com/
MCP tools · 21 exposed · ~6,354 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
account ~261

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.

NameTypeReqDescription
actionstringyesWhich account operation to run.
amount_centsinteger–donate: amount in cents (100-500000).
sku_idstring–checkout: SKU id from plans (e.g. "plus_monthly", "pro_annual").

No output schema declared.

No examples provided.

agent_manage ~777

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 af02b…

NameTypeReqDescription
actionstringyesWhat to do
add_collectionsarray–update: grant or re-role only these lines; others are kept. [{slug, role}] or bare slugs (reader).
can_read_my_memoriesboolean–Deprecated -- use owner_access.
collectionsarray–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_coll…
confirmstring–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).
from_agentstring–merge source (alias for name).
namestring–Agent name. For merge = SOURCE (consumed).
owner_accessstring–Agent access to your personal memories: none/reader/member. With update.
remove_collectionsarray–update: revoke only these slugs; others are kept.
to_agentstring–merge destination (absorbs source). Default = your primary.
to_collectionstring–merge: temporarily disabled, refused with 503 (task 8cfe199b). Use to_agent.

No output schema declared.

No examples provided.

artifact_delete ~63

Delete an artifact: every revision and its pointer memory. Permanent. confirm must equal the artifact name. memory_delete refuses a pointer; use this.

NameTypeReqDescription
artifact_idstringyes–
confirmstring–The artifact name, e.g. "assertions.md".

No output schema declared.

No examples provided.

artifact_history ~51

List the revisions of an artifact (rev_id, parent, seq, time, author, pinned) and its heads. conflict=true means divergent heads to merge.

NameTypeReqDescription
artifact_idstringyesPointer memory id.

No output schema declared.

No examples provided.

artifact_orphans ~39

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

artifact_pin ~49

Pin a revision so retention thinning never removes it (pinned=false unpins).

NameTypeReqDescription
artifact_idstringyes–
pinnedboolean–Default true.
rev_idstringyes–

No output schema declared.

No examples provided.

artifact_read ~148

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.

NameTypeReqDescription
artifact_idstringyesPointer memory id.
occurrenceinteger–0-based pick among duplicate headings.
pageinteger–0-based 40,000-character page.
rev_idstring–Older revision. Omit=head.
section––Markdown heading path (array) or JSON pointer string.

No output schema declared.

No examples provided.

artifact_write ~501

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.

NameTypeReqDescription
artifact_idstring–Pointer memory id. Omit to create.
base_rev_idstring–UPDATE: the head rev_id you read.
bodystring–Whole document text.
collectionstring–CREATE: shared collection. Omit=default. "me"=personal.
contentstring–Replacement for section.
macro_topicsarray–CREATE: project/domain.
merged_rev_idsarray–Other heads this write resolves.
namestring–File name; extension sets the format (.md markdown, .json json, else text).
occurrenceinteger–0-based pick when the section path matches more than one heading.
section––Markdown heading path (array of heading texts) or JSON pointer string.
summarystring–CREATE: pointer memory text. Front-loaded: what the document is + why.
topicsarray–CREATE: pointer search words.

No output schema declared.

No examples provided.

collection_manage ~389

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.

NameTypeReqDescription
actionstringyesWhat to do
confirmstring–delete: 2-step. Call without it -> refusal names slug + member/memory impact; repeat with confirm:"<slug>". Permanent.
memory_idsarray–Memory IDs to publish (copy in; originals kept).
namestring–Collection name.
new_namestring–update: new display name (slug/keys unchanged). Type change not via update.
rolestring–"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.
typestring–"collaborative" = everyone can read and write. "knowledge_pack" = only the owner writes, others can read. Default: collaborative.
userstring–Email or agent name to add/remove.

No output schema declared.

No examples provided.

init_core_memories ~268

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.

NameTypeReqDescription
machine_idstring–Machine id for workspace paths (run hostname). e.g. p620. Omit if no filesystem.
querystring–Optional turn-one search (piggybacks on init). Top 3 auto-expanded if score >= 80.

No output schema declared.

No examples provided.

memory_add ~1,036

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).

NameTypeReqDescription
artifactstring–Commit SHA or filename -> auto-added to topics. e.g. "f4e5d6c", "oauth.py".
collectionstring–Shared collection by name. Omit=default. "me"/"personal"/agent name=own namespace; "owner"/"parent"=account primary (member-gated).
contentstring–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.…
ephemeralboolean–Auto-expire 90d.
expires_atstring–YYYY-MM-DD, or "never". Overrides ephemeral.
forceboolean–Skip dup check. Testing only.
macro_topicsarray–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…
memoriesarray–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.
refstring–Parent task/ticket id -> auto-added to topics. e.g. "a1b2c3d4", "GH-142".
signalstring–Also signal recipient (email, agent, "owner"). Needs a SHARED collection ("me"/personal rejected up-front — nothing stored).
statusstring–Initial task status. Default pending.
stepsarray–Task checklist -> "- [ ]" boxes. Requires title.
summarystring–Task prose: state/blockers/decisions -> "## Summary" block. type task/task_done. Not type="summary" (that is memory_consolidate).
titlestring–Task title (structured). Requires type="task". Not with content.
topicsarrayyesREQUIRED. Then the specific search keywords: single lowercase, no _ or -. First = "user" for preferences. Not macro_topics.
typestring–fact=knowledge, preference=user pattern, decision=choice+reason, path=location, task=actionable, task_done=complete, result=an output or finding.

No output schema declared.

No examples provided.

memory_add_batch ~387

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.

NameTypeReqDescription
collectionstring–Shared collection by name. Omit=default. "me"/"personal"/agent name=own namespace; "owner"/"parent"=account primary (member-gated).
forceboolean–Skip dup check. Testing only.
memoriesarrayyesArray of memory objects to store
signalstring–Also signal recipient with ALL stored ids. Needs a SHARED collection ("me"/personal rejected up-front — nothing stored).

No output schema declared.

No examples provided.

memory_consolidate ~243

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.

NameTypeReqDescription
collectionstring–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.
contentstringyesThe summary. Present tense, self-contained: what it is, state, decisions, open questions.
topicstringyesTopic to summarize. Lowercase. e.g. "python".

No output schema declared.

No examples provided.

memory_deep_search ~241

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).

NameTypeReqDescription
collection_filterstring–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.
expandboolean–Full content for all results (50K+ tokens). Dedicated large-context agents only.
querystringyesSearch query -- 2+ keywords.
type_filterstring–Filter by type: fact/preference/decision/path/task/task_done/summary/result. Omit=all.

No output schema declared.

No examples provided.

memory_delete ~62

Delete memories by ID. Permanent. memory_delete(["id1","id2"]). Delete by filter: memory_search first, collect ids, then delete.

NameTypeReqDescription
idsarrayyesMemory IDs to delete. e.g. ["abc-123","def-456"].

No output schema declared.

No examples provided.

memory_edit ~870

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

NameTypeReqDescription
add_macro_topicsarray–macro_topics to add; the rest stay.
add_stepsarray–Append checklist items (milestones). Re-embeds.
add_topicsarray–Topics to add; the rest stay.
artifactstring–Commit SHA or filename -> merged into topics. e.g. "f4e5d6c".
collectionstring–Collection for signal routing (only with signal param).
contentstring–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.
edit_stepobject–Rewrite a step's text, preserving checkbox state. Re-embeds.
ephemeralboolean–Set time-bound (auto-expires in 90 days)
expires_atstring–YYYY-MM-DD, or "never". Overrides ephemeral.
macro_topicsarray–New macro_topics (REPLACES all). 1-3 lowercase.
memory_idstringyesID of memory to edit
outputstring–Durable finding on this update -> linked fact memory (inherits task topics). Atomic, front-loaded. Over-length rejected. Many findings -> memory_add.
refstring–Parent task/ticket id -> merged into topics. e.g. "a1b2c3d4".
remove_macro_topicsarray–macro_topics to drop; the rest stay.
remove_stepsarray–Remove steps by 0-based index (pre-call state). Re-embeds.
remove_topicsarray–Topics to drop; the rest stay. At least one must remain.
set_statusstring–Task status. "done" auto-sets type=task_done (reverting reverts); type follows status. See Combine rules.
set_summarystring–Replace the task's "## Summary" block ("" clears). Re-embeds. Not type="summary" (that is memory_consolidate).
signalstring–Also signal recipient (email, agent, "owner") with this memory_id. Needs a SHARED collection ("me"/personal rejected).
togglearray–0-based checkbox indices to flip. e.g. [0,2]. See Combine rules.
topicsarray–New topics (REPLACES all). Search words, lowercase.
typestring–New type: fact/preference/decision/path/task/task_done/result

No output schema declared.

No examples provided.

memory_retrieve ~68

Get full content by ID. Use when search returned complete=false. Batch: memory_retrieve(["id1","id2"]). Skip if complete=true (preview is already full).

NameTypeReqDescription
idsarrayyesMemory IDs to fetch. e.g. ["abc-123","def-456"].

No output schema declared.

No examples provided.

memory_search ~198

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).

NameTypeReqDescription
collection_filterstring–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.
expandboolean–Full content for all results (~16K tokens/page). Dedicated research agents only.
querystringyesSearch query -- all relevant nouns.
type_filterstring–Filter by type: fact/preference/decision/path/task/task_done/summary/result. Omit=all.

No output schema declared.

No examples provided.

message ~227

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.

NameTypeReqDescription
actionstringyessend=post, check=read pending, ack=DELETE for every session of your name.
collectionstring–send: shared collection (both parties must be members).
expires_hoursinteger–send: hours until the message is deleted unread, 24-720. Default 168.
message_idsarray–ack: message IDs to delete.
recipientstring–send: agent name, email, or "owner" (the human account holder).
textstring–send: the message, up to 4000 characters.

No output schema declared.

No examples provided.

signal ~295

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.

NameTypeReqDescription
actionstringyessend=post, check=read pending, ack=close (a non-destructive stamp; nothing is deleted).
collectionstring–send: shared collection (both parties must be members).
expires_hoursinteger–For send: hours until signal expires. Default 48.
memory_idsarray–For send: memory IDs to point the recipient to.
recipientstring–send: agent name, email, or "owner" (the human account holder).
signal_idsarray–ack: signal IDs to close -- ones nothing further is owed on.

No output schema declared.

No examples provided.

task_feed ~181

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.

NameTypeReqDescription
collectionstring–Scope to one collection. Omit=personal + all collections.
limitinteger–Max tasks to return. Default 32, max 500.
sincestring–ISO timestamp, or 24h / 2d / yesterday. Returns tasks updated after it.
statusstring–Omit for every task not done; done lists finished ones.
topicstring–Filter to one topic.

No output schema declared.

No examples provided.

Install

How do I install the Gnosis Memory MCP server?

Gnosis Memory is a hosted endpoint at https://gnosismemory.com/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · gnosismemory.com

# add to Claude Code
claude mcp add --transport http com-gnosismemory-memory 'https://gnosismemory.com/'
Common questions

What is the Gnosis Memory MCP server?

Gnosis Memory is an MCP server listed in the public MCP registry as com.gnosismemory/memory. Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in. This page covers its hosted endpoint (https://gnosismemory.com).

Is the Gnosis Memory MCP server safe to use?

Gnosis Memory scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Gnosis Memory MCP server expose?

Gnosis Memory exposes 21 tools: init_core_memories, memory_add, memory_add_batch, memory_search, memory_deep_search, and 16 more. Their descriptions and schemas cost roughly 6,354 tokens of context every time the server is loaded.

Does the Gnosis Memory MCP server require authentication?

Yes. Gnosis Memory asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Gnosis Memory MCP server still maintained?

Gnosis Memory is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Gnosis Memory MCP server?

VerifyMCP ran 13 checks on Gnosis Memory, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.