Home / MCP registry index / ai.ctxstore/ctxstore-mcp
ctxstore — memory that follows you across models
ai.ctxstore/ctxstore-mcp in the official MCP registry.
Endpoint https://mcp.ctxstore.ai/mcp. Source: github.com/ctxstore-ai/ctxstore-mcp.
The registry describes it as: Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
We read its 32 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
accept_invite bind_agent decline_invite delete_fact get_fact get_fact_history get_session_seed get_stats ghost_mode index_recent index_search index_stats introduce_yourself leave_grant list_facts_by_key_prefix list_invites list_workspaces load_context mark_salient move_fact reinforce_fact resume_session revoke_grant search_context search_facts setup_account store_fact store_facts store_session_summary switch_workspace wake_status watch_events
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-ctxstore-ctxstore-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.