# chat-recall (io.github.munhq/chat-recall@0.6.6) > Source: > Published: 2026-09-14 15:58:29+00:00 [← Index](/leaderboard) # chat-recall One searchable history across every AI coding tool, with secret scanning and a shared task board. The current version, v0.6.6, was published to the official MCP registry on 2026-09-14. It is distributed as chat-recall on npm and as a hosted remote over streamable-http, filed under Search by this index, and declares 4 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; [the index's current counts](/stats) put this record in context. ## Using chat-recall in Claude, Cursor, Gemini CLI, Cline, or Zed? MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and **HOLDs the call** when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use **Install this server** for that). Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less ``` uv tool install mcpindex-gate && mcpindex-config-wire ``` [method](/methodology) Semantic screen found no manipulation pattern in the description. Conformance probe not yet run. `mcpindex.integrity.description` passINFO evidence“No malicious instructions”via static_description - - Semantic screen only - the deterministic conformance probe has not run on this server - - Confidence is reported but not yet calibrated (v1) - - Screen reads the tool description, not the live behavior - - advisory - - registry description only no input schema - - screen model 8b - - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page. Own this server? [Screen its description →](/screen) ## That verdict was true at screening time (snapshot 2026-09-14). Contracts can change after screening, with no version bump. The gate pins chat-recall’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday. [See your first HOLD in 2 minutes →](/guides/install-the-gate-first-hold) Related: [how to trust an MCP server](/guides/how-to-trust-an-mcp-server) · [screen before install](/guides/screen-mcp-server-before-install) · [silent contract drift](/guides/mcp-silent-contract-drift) People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land. ``` [Independent trust record for chat-recall](https://mcpindex.ai/server/io-github-munhq-chat-recall) - screening verdict, registry provenance, and contract drift monitoring. Independent trust record for chat-recall - screening verdict, registry provenance, and contract drift monitoring. ``` A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does. ``` [![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-munhq-chat-recall)](https://mcpindex.ai/server/io-github-munhq-chat-recall) mcpindex verdict ``` `CHAT_RECALL_SERVER` Server to sync to. Defaults to the hosted service at https://chatrecall.dev; set it to your own instance to self-host. Self-hosting is free for one person. `CHAT_RECALL_MCP_PROFILE` Which tools to register: "lean" (default, 28 tools — tool choice degrades as the list grows) or "full" (all 62 tools, plus recall_help — a directory of the rest; 4 code-intelligence tools register only with the codeindex companion on PATH). Every tool works when called by name either way. `CHAT_RECALL_NO_DAEMON` Set to 1 to load the whole server inside each session. By default every session with the same profile and server shares one background daemon, and each session is a thin relay onto it — the engine is loaded once per machine instead of once per session. Turn it off for a sandbox with no writable runtime directory. `CHAT_RECALL_DAEMON_IDLE_SECS` Seconds with no session attached before the shared daemon exits and returns its memory. Default 900. Set 0 to keep it resident. [methodology](/methodology) [Fodda Topic & Trend Researchai.fodda/topic-research](/server/ai-fodda-topic-research) Trend, stats & insight search across PSFK expert graphs with citable sources. [ProductNowai.productnow/productnow](/server/ai-productnow-productnow) Connect AI agents to ProductNow's context engine to search, create, review, and act. [io.github.musikalienhandel-de/mcp-serverio.github.musikalienhandel-de/mcp-server](/server/io-github-musikalienhandel-de-mcp-server) Product search for musikalienhandel.de: sheet music, GEWA instruments, B-Ware/clearance stock.