MCP server

ctxstore — memory that follows you across models Official

ai.ctxstore/ctxstore-mcp

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

ctxstore.ai (verified by the MCP Registry)

Status

Working at last check

Tools

33

Token cost

About 9,884 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http ctxstore-mcp https://mcp.ctxstore.ai/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.ctxstore-mcp]
url = "https://mcp.ctxstore.ai/mcp"

Gemini CLI

{"mcpServers":{"ctxstore-mcp":{"httpUrl":"https://mcp.ctxstore.ai/mcp"}}}

Cursor

{"mcpServers":{"ctxstore-mcp":{"url":"https://mcp.ctxstore.ai/mcp"}}}

VS Code

{"servers":{"ctxstore-mcp":{"type":"http","url":"https://mcp.ctxstore.ai/mcp"}}}

Antigravity

agy mcp add ctxstore-mcp https://mcp.ctxstore.ai/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"ctxstore-mcp","server_url":"https://mcp.ctxstore.ai/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"ctxstore-mcp","server_url":"https://mcp.ctxstore.ai/mcp"}

Tools

• accept_invite ~318 tokens
  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
• bind_agent ~251 tokens
  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 bind
• decline_invite ~112 tokens
  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.
• delete_fact Deletes data · ~116 tokens
  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.
• get_fact ~202 tokens
  Retrieve a fact by its exact key — deterministic, never misses. Use get_fact for self-notes: get_fact(key='agent:<name>:self-note:opening') or get_fact(key='agent:<name>:self-note:closing'). search_facts misses self-notes because their embedding similarity scores below other identity facts — get_fac
• get_fact_history ~132 tokens
  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.
• get_session_seed ~115 tokens
  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.
• get_stats ~91 tokens
  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.
• ghost_mode ~133 tokens
  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).
• index_recent ~190 tokens
  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), namespa
• index_search ~238 tokens
  Filtered search over the tenant activity index. Find what a specific agent wrote, what happened in a namespace, or recent creates/updates/deletes. Useful for coordination: "what did emily_dev store in the sprint namespace today?"
• index_stats ~84 tokens
  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.
• introduce_yourself ~228 tokens
  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:<model>-<date> Include: what model you are, what platform you're running on, and anything you
• invite ~323 tokens
  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 return
• leave_grant Changes accounts · ~116 tokens
  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.
• list_facts_by_key_prefix ~384 tokens
  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 fac
• list_invites ~266 tokens
  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
• list_workspaces ~175 tokens
  The places this account's memory is organised into: its own projects (anything written under project:<slug>:*, newest activity first), the workspaces other people have granted it (enter one with switch_workspace(name=<grantor>)), and, for a sharer, who they invited and whether each person accepted a
• load_context ~1114 tokens
  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: pas
• mark_salient ~355 tokens
  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 ou
• move_fact ~198 tokens
  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.
• reinforce_fact ~356 tokens
  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
• resume_session ~53 tokens
  Call to load session continuity. Last session: no prior session.
• revoke_grant Changes accounts · ~104 tokens
  Revoke a pending invitation or active grant as the GRANTOR (owner of the shared namespace). Idempotent. Grantees use decline_invite / leave_grant.
• search_context ~190 tokens
  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.
• search_facts ~485 tokens
  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 s
• setup_account ~894 tokens
  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: crea
• store_fact ~560 tokens
  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,
• store_facts ~289 tokens
  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 da
• store_session_summary ~548 tokens
  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
• switch_workspace ~309 tokens
  Narrow this session's memory to one project: name='<slug>' scopes recall, the wake bundle, self-notes and the default namespace for new facts to project:<slug>:* (identity and conventions always ride along). Returns the narrowed bundle right away. name='' widens back to the whole account. Sticky for
• wake_status ~523 tokens
  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
• watch_events ~432 tokens
  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_si

Browse

• Email
• Databases
• Memory for agents
• Searching your documents (RAG)

Related MCP servers

• ChronoKey
  MCP tools: timestamps, UUID v4, gas prices, domain WHOIS, text extraction, and persistent memory.
• emem, the verifiable memory protocol for the physical world
  Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.
• MemoryPlugin
  Give every AI you use one shared, permanent memory. Store once, recall in whichever AI you open.
• MemoryRouter
  Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
• WorkingMemory
  Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
• GadgetHumans API Hub
  49 MCP tools free (rate-limited) + x402 pay-per-call on Base. Flagship: Token Verdict, $0.02.
• Agentdevx
  Give your AI hands. Identity, credential vault, and API gateway for autonomous agents.
• Sayba AI Agent Social Platform
  AI Agent social network with 23 MCP tools for social, tasks, skills, and XC token economy.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/ai.ctxstore/ctxstore-mcp.svg)](https://aptlynx.net/servers/ai.ctxstore/ctxstore-mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents