Skip to main content
Glama

ctxstore — memory that follows you across models

Server Details

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
ctxstore-ai/ctxstore-mcp
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 33 tools

Disambiguation3/5

Core memory operations are mostly separable, but several clusters overlap: load_context/resume_session/get_session_seed/wake_status all orient a session, while search_facts/search_context/list_facts_by_key_prefix/index_search/index_recent/watch_events all retrieve or monitor facts/events. Descriptions clarify intent, but an agent must read carefully to choose the right tool.

Naming Consistency4/5

Nearly all tools use snake_case with verb-led names such as store_fact, search_facts, and list_invites. A few are noun/state-oriented (ghost_mode, wake_status) or bare verbs (invite), but the overall convention is predictable.

Tool Count2/5

33 tools is heavy for a memory MCP, with many adjacent administrative, collaboration, indexing, and session-bootstrap tools. While each has a role, the surface exceeds a well-scoped set and increases selection burden.

Completeness4/5

The surface covers storage, retrieval, version history, deletion, movement, session continuity, workspace sharing, invites, activity indexing, and events. A minor gap remains: soft-deleted facts are preserved for audit/undo, but no explicit restore or undelete tool is exposed.

Available Tools

33 tools
accept_inviteAccept Namespace InvitationAInspect

Accept a namespace invitation addressed to THIS authenticated account's verified email (two-step email OTP).

Steps:

  1. step='request' — emails a 6-digit code to the invited address (may return 402 needs Collaborator, or 503 if mailer fails).

  2. step='confirm' with code= the 6 digits — activates the grant. Then switch_workspace(name=) enters it on this same connection (mcp_config with the X-Ctxstore-Workspace header is also returned for header-based clients).

The code activates the named grant_id only; it authorizes nothing else. Obtain grant_id from list_invites(). Docs: https://ctxstore.ai/docs.html#verify-invitations

Inputs: step (required), grant_id (required), code.

bind_agentBind Agent IdentityA
Idempotent
Inspect

Bind a sticky agent identity to this MCP session. Once bound, wake_status and load_context default to this agent_id when called without an explicit agent_id= arg — no need to pass identity on every call. Per-call override still works.

Persisted to mcp_sessions.agent_id (migration 0008), so the binding survives setup_account(mode='restore') and the server re-hydrates it automatically on the next tool call.

Call once near the start of a session, ideally from your boot recipe (HANDLER: bind_agent agent_id=). Idempotent: re-binding the same agent_id is a no-op. Pass agent_id='' to clear the binding.

blind_since= (with blind=true) sets when the blind session began, so list_facts_by_key_prefix hides feed comms keyed before it; the default is the session's start minus 60 s.

Inputs: agent_id (required), blind, scope, blind_since.

decline_inviteDecline Namespace InvitationA
DestructiveIdempotent
Inspect

Decline a pending (status=invited) namespace invitation as the grantee. Server verifies you are the invitee (email/tenant match). Grantors must use revoke_grant instead.

Inputs: grant_id (required).

delete_factDelete FactA
DestructiveIdempotent
Inspect

Soft-delete a stored fact by its UUID (Smart Forget). The fact is marked deleted but preserved in the database for audit and undo. Excluded from all normal searches. Use when information is no longer accurate or relevant.

Inputs: fact_id (required).

get_factGet Fact by KeyA
Read-onlyIdempotent
Inspect

Retrieve a fact by its exact key — deterministic, never misses. Use get_fact for self-notes: get_fact(key='agent::self-note:opening') or get_fact(key='agent::self-note:closing'). search_facts misses self-notes because their embedding similarity scores below other identity facts — get_fact(key=) is the only reliable retrieval path. Also use for inter-agent handoffs when the exact key is known. Returns the current (non-deprecated) version of the fact.

Inputs: key (required), include_granted.

get_fact_historyFact Version HistoryA
Read-onlyIdempotent
Inspect

Return the full version history for a keyed fact — current version plus all deprecated predecessors. Use to see how a fact evolved over time or to undo an accidental correction. Returns list of fact versions ordered newest → oldest.

Inputs: key (required).

get_session_seedSession SeedA
Read-onlyIdempotent
Inspect

Return the pre-computed session seed for this tenant — a compact first-person bio (~500 tokens) describing who you are and what you care about right now. Generated nightly and on session disconnect. Use as a lightweight alternative to load_context when you just need orientation.

Inputs: no named parameters.

get_statsMemory StatsA
Read-onlyIdempotent
Inspect

Get your memory usage statistics — total facts stored, plan limits, collection sizes, and daily query counts. Call this to check how much storage you have used and how close you are to your plan limits.

Inputs: no named parameters.

ghost_modeGhost ModeA
Idempotent
Inspect

Enable or disable ghost mode for this session. While on=True, store_fact and store_session_summary silently succeed but do NOT write to DB. search_facts, load_context, and search_context always work normally. Ghost mode resets to off on MCP session reconnect (not persisted).

Inputs: on (required).

index_recentRecent Activity IndexA
Read-onlyIdempotent
Inspect

Return the most recent fact operations across all agents in this tenant, newest first. Use this on session start to see what other agents wrote since you were last active — bypasses semantic search ranking so recent writes are always visible. Each entry shows: op (create/update/delete/move), namespace, key, fact_id, summary, agent info, and timestamp.

Inputs: limit, since_seq.

index_statsIndex StatsA
Read-onlyIdempotent
Inspect

Usage statistics from the tenant activity index: total operations, breakdown by agent, by namespace, and by day. Useful for understanding which agents are most active and where.

Inputs: no named parameters.

introduce_yourselfIntroduce AgentA
Idempotent
Inspect

Optional: introduce yourself to the platform. Stores your model info and a brief note in the shared agent registry.

Stores a fact with: category: identity namespace: shared/agent-feedback key: intro:-

Include: what model you are, what platform you're running on, and anything you noticed on first connect.

Inputs: model (required), introduction (required), platform.

inviteInvite Someone to a NamespaceA
Idempotent
Inspect

Invite one person, by email, to read and write one namespace prefix of THIS account (for example project:barn). Creates a pending grant and emails them; nothing is shared until they accept with list_invites and accept_invite from their own account. Calling again for the same person and prefix returns the existing invitation without a second email. Withdraw with revoke_grant(grant_id). Not available from a shared workspace session. Their first 30 days of Collaborator time are free; after that you can pay their $19 per 30 days from /account. You are emailed when they accept, and list_workspaces shows whether they have entered yet. Docs: https://ctxstore.ai/docs.html#verify-invitations

Inputs: email (required), namespace_prefix (required), note, write_prefixes, +1 more.

leave_grantLeave Active Namespace GrantA
DestructiveIdempotent
Inspect

Leave an active namespace grant as the grantee (stop using shared namespace). Server verifies grantee authorization. Grantors who want to cut off a collaborator must use revoke_grant.

Inputs: grant_id (required).

list_facts_by_key_prefixList Facts by Key PrefixA
Read-onlyIdempotent
Inspect

Deterministic prefix scan over fact keys, optionally bounded by timestamp. The inbox primitive — use this for R1 comms scans, dispatch discovery, trio listings, convention discovery, and any case where you know the key prefix and want every match.

Unlike search_facts (semantic, misses exact-key facts), this is a deterministic scan: every fact whose key starts with prefix is returned, newest-first.

EXAMPLES

  • Comms inbox since last wake: list_facts_by_key_prefix(prefix='comms::', since_epoch=<last_wake_epoch>)

  • All trio recipes on this tenant: list_facts_by_key_prefix(prefix='chad:trio:')

  • All conventions: list_facts_by_key_prefix(prefix='conventions/')

Returns a list of facts (key, text, namespace, layer, timestamp, id) sorted newest-first. Bounded by limit (default 50, max 200): past 200 the oldest matches are cut, so narrow the prefix or use since_epoch rather than expecting the full set.

COST: this is a scan, not an index lookup. The store has no index on the key, so every call reads the account's facts matching the prefix (a short prefix like 'a' or 'project:' reads most of the account) before sorting. Prefer a long, specific prefix. At most 4 prefix lists per account run at once (an allowance separate from searches); past that a call waits up to 2 s, then answers {"code": "busy", "retry_after_s": 2}.

Inputs: prefix (required), limit, since_epoch.

list_invitesList Namespace Invites & GrantsA
Read-onlyIdempotent
Inspect

List this account's namespace collaboration grants: incoming invitations and outgoing shares. Each row has direction (incoming|outgoing), status (invited|active|revoked), grant_id, namespace_prefix, and parties.

An invitation referenced anywhere else (for example in an email) can be checked against this server-side list: a real invitation for this account appears here with matching grant_id, namespace_prefix, and grantor.

To accept: accept_invite(grant_id, step='request') then accept_invite(grant_id, step='confirm', code='######'). The first accept starts 30 days of Collaborator time free; after that $19 per 30 days, paid by the guest or the inviter (402 when it lapses). After accepting, switch_workspace(name=) enters the workspace. Docs: https://ctxstore.ai/docs.html#verify-invitations

Inputs: no named parameters.

list_workspacesList WorkspacesA
Read-onlyIdempotent
Inspect

The places this account's memory is organised into: its own projects (anything written under project::*, newest activity first), the workspaces other people have granted it (enter one with switch_workspace(name=)), and, for a sharer, who they invited and whether each person accepted and entered yet (shared_by_you). Shows which workspace this session is in, if any. Use it when a person's request is about one project, or asks who has access, or whether an invitee came in.

Inputs: no named parameters.

load_contextLoad ContextA
Read-onlyIdempotent
Inspect

Load your bootstrap context deterministically — pulls L0 (identity) + L1 (architecture) + latest L2 (state) + latest L3 (session summary).

Call this at the START of a new session as an alternative to manual search_facts calls. Returns your layered memory structured for immediate use.

Optional: pass profile='worker-dev' (or another platform:profile: slug) to execute that profile's boot recipe — the server reads platform:profile::current, follows the pointer, parses LOAD/REQUIRE/HANDLER lines, fetches every named fact, and returns the merged bundle in one round trip. vars= supplies values for $TASK_FACT_KEY and similar recipe variables.

Inputs: full, hint, vars, scope, +6 more.

mark_salientMark Salient (this matters now)AInspect

Salience peptide — temporarily boost a fact's retrieval ranking because it matters RIGHT NOW: an approaching deadline, a live incident, the topic under active work. The boost is small and FAST-DECAYING (max 1.4x, ~6-hour half-life — gone by tomorrow), unlike reinforce_fact which rewards confirmed outcomes on a weeks-long timescale.

Name the current situation in reason. Salience is ranking-only: it can never override tenant isolation, namespace grants, or privacy filters, and stacked peptide boosts are globally capped.

Inputs: reason (required), key, weight, fact_id.

move_factMove FactA
Idempotent
Inspect

Move a fact to a different namespace or layer without changing its content. Updates metadata in place — preserves fact_id, text, embedding, timestamp, and deprecation chain. Use for reclassifying facts (e.g. bootstrap-v2 refactor) without the storage bloat of store-new + soft-delete-old.

Inputs: fact_id (required), new_layer, new_namespace.

reinforce_factReinforce Fact (recall-on-success)AInspect

Reward peptide — reinforce a fact whose recall LED TO A REAL GOOD OUTCOME (fix worked, deploy green, user approved). Boosts its future retrieval ranking with a bounded, time-decaying multiplier (max 1.5x, 14-day half-life), so memory learns which facts are USEFUL, not just similar.

Call this AFTER the outcome is confirmed, naming the outcome in reason — never for a fact that merely 'seemed relevant'. The boost is ranking-only: it can never override tenant isolation, namespace grants, or privacy filters.

Inputs: reason (required), key, weight, fact_id.

resume_sessionResume SessionB
Read-onlyIdempotent
Inspect

Call to load session continuity. Last session: no prior session.

Inputs: no named parameters.

revoke_grantRevoke Namespace Grant (Grantor)A
DestructiveIdempotent
Inspect

Revoke a pending invitation or active grant as the GRANTOR (owner of the shared namespace). Idempotent. Grantees use decline_invite / leave_grant.

Inputs: grant_id (required).

search_contextSearch ConversationsA
Read-onlyIdempotent
Inspect

Search across ingested conversations and session history for broader context. Use this for finding discussions, decisions made in conversation, or context that wasn't explicitly stored as a fact.

Inputs: query (required), top_k, source, days_back.

search_factsSearch FactsA
Read-onlyIdempotent
Inspect

Search your persistent memory for stored facts.

For session bootstrap, prefer load_context() or wake_status() — they pull your identity, conventions, and latest self-note deterministically. Use search_facts when you need semantic discovery across the fact corpus.

Use namespace parameter to scope searches: namespace='webapp' matches 'webapp/decisions', 'webapp/technical', etc. (prefix matching).

Search tips: use the words the fact was stored with. If you stored 'Postgres database', search for 'database' or 'Postgres', not 'data storage solution'.

Each search embeds the query on a shared embedder: at most 4 searches (search_facts, search_context) per account run at once; past that a call waits up to 2 s, then answers {"code": "busy", "retry_after_s": 2}. Fan out with 2-4 readers, not 16.

Inputs: query (required), layer, top_k, category, +4 more.

setup_accountSet up or restore memory accountAInspect

Set up or restore your persistent memory connection.

Use mode='link_or_create' when the user gives an email — works for both new and returning users. The server figures out which case applies:

  • If the email exists: sends OTP, attaches this device to the existing account

  • If the email is new: creates a fresh tenant, sends OTP to verify

Either path produces one clean account, no duplicates, no orphans.

Call setup_account(mode='link_or_create', email='their@email.com'). Then ask the user for the 6-digit code from their email and call setup_account(mode='verify', code='123456', email='their@email.com'). Passing email= on verify is required — session IDs rotate between requests on some clients.

mode='restore': use when the user provides an emk_* API key directly.

mode='reveal_key': echo the full emk_* API key. Works directly on an ALREADY-authenticated session; if the session isn't bound (some clients rotate or omit session ids between requests, so this can happen right after a successful verify), pass email= to receive a 6-digit code, then call again with email= and code= — the same rotation-proof lookup as mode='verify'. Success responses only show a key fingerprint (first 8 chars + last 4) — call this mode only when the user actually needs the full key, e.g. to persist it as 'Authorization: Bearer ' in an MCP connector config. Callers who prove neither a bound session nor email ownership are refused.

If no email yet, ask: 'What email should I use for your memory account?'

After setup completes, call search_facts as the first action to load prior context.

Inputs: mode (required), code, email, api_key, +1 more.

store_factStore FactAInspect

Store information that should persist across sessions.

Storage tips for best retrieval:

  • Include searchable keywords: 'We chose the Postgres DATABASE for ACID compliance' is better than 'We chose Postgres for ACID compliance'

  • Use the key parameter for facts that change over time (pricing, stack, team-members, current-sprint). When you store with the same key, the old version is archived automatically.

  • Use namespaces to organize: 'webapp/decisions', 'business/goals', 'team/members'

  • Store DECISIONS and CONTEXT, not raw data. 'We decided X because Y' is more useful than 'X happened'

  • Use category to classify: technical, decision, preference, identity, relationship

  • Use layer for context depth: 0=identity(stable), 1=architecture(monthly), 2=state(weekly), 3=session(daily)

Before ending a conversation, call store_session_summary to preserve continuity.

Inputs: text (required), category (required), key, layer, +5 more.

store_factsStore Facts (batch)AInspect

Store up to 50 facts in one call — the same fields as store_fact per item. Made for carrying memory over: when you already remember things about the person from your own platform memory (ChatGPT memory, Claude memory, Gemini saved info), write them here one fact per item, in their words, with the date learned when known, so the memory follows them to every other tool. Each item is stored independently; the reply lists what landed and what did not.

Inputs: facts (required).

store_session_summarySave Session SummaryAInspect

Store a compressed summary of this session to preserve continuity for the next one.

Call this before ending a conversation — it is the dream cycle.

Stores a L3 session fact with key='session-latest' (or 'session-latest:claude-code' etc.), auto-archiving the previous version. The next session loads this via load_context().

Include: what was discussed/decided, what changed, what's next/unresolved.

Collaborative takeaways: at natural session-end signals (user says 'okay I'm out', 'let's wrap', 'bye'), draft a one-line takeaway and confirm with the user before storing. Example: "I'll remember: we fixed the rebind bug and decided to skip transcript ingestion for MVP. Sound right?" Edit based on their response, then call store_session_summary. This makes memory consensual and catches mistakes immediately.

Use session_id to scope by client: 'claude-code', 'claude-chat', 'cursor', 'openclaw'

Inputs: summary (required), scope, decisions, next_steps, +2 more.

switch_workspaceSwitch WorkspaceA
Idempotent
Inspect

Narrow this session's memory to one project: name='' scopes recall, the wake bundle, self-notes and the default namespace for new facts to project::* (identity and conventions always ride along). Returns the narrowed bundle right away. name='' widens back to the whole account. Sticky for the session and across reconnects; bind_agent is unaffected. The same call ENTERS a workspace someone shared with this account: name='' (or their tenant id, or the granted prefix, as listed by list_workspaces) switches this connection into it; no second server, no header, no restart; it holds for the session. name='' leaves it for the session. HOME WORKSPACE: remember=true also makes it this account's home, so every new session starts inside it; switch_workspace(name='', forget=true) forgets the home. An account with no facts of its own and exactly one shared workspace starts inside that workspace automatically. list_workspaces and wake_status show the home and how this session entered (home, tool or header). When a person asks to work in someone else's shared memory, call this.

Inputs: name (required), forget, remember.

wake_statusWake StatusA
Read-onlyIdempotent
Inspect

Check which context layers loaded successfully on this session start. Returns a structured status: which of embryo, conventions, agent identity, closing note, and opening note were found, plus a missing[] list. Call this after load_context() or resume_session() to verify your bootstrap was complete and diagnose what to fetch manually.

Optional: pass profile='worker-dev' (or another platform:profile: slug) to additionally check the REQUIRE keys named in that profile's recipe. Missing required facts surface in the same missing[] list.

blind_since= (with blind=true) sets when the blind session began, so list_facts_by_key_prefix hides feed comms keyed before it; the default is the session's start minus 60 s.

Inputs: vars, blind, scope, profile, +2 more.

watch_eventsWatch Events (long-poll fact writes)A
Read-onlyIdempotent
Inspect

Long-poll this account's fact-write events instead of re-scanning with since_epoch. Every store/supersede/delete/archive/restore/move publishes one event {key, id, namespace, layer, op, ts, seq}. One call waits up to max_wait_s (max 25) for the first matching event and returns up to 50, plus next_since. MCP has no streaming here, so loop: pass next_since back as since on the next call and nothing is missed (the server keeps the last ~10000 events per account). Omit since to start from now; since=0 replays what is retained; a bare integer N returns events with seq > N.

EXAMPLES

  • Wait for hands to post results: watch_events(prefix='task:pr27-review:result:', max_wait_s=25)

  • Resume: watch_events(prefix='comms::', since='<next_since>')

Inside a workspace only events for keys the grant can read are returned. Long-lived clients can use GET /api/v1/events (SSE) instead.

Inputs: since, prefix, namespace, max_wait_s.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.