ctxstore — memory that follows you across models
ai.ctxstore/ctxstore-mcp · v1.1.2 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
Source: https://github.com/ctxstore-ai/ctxstore-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 33 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_fact). Require confirmation before the agent calls them. |
What was checked
- https://mcp.ctxstore.ai/mcp: answers without auth
Public tools: 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, invite, 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
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/ai-ctxstore-ctxstore-mcp-6e138cd4)