Khwan (ai.khwan/khwan-mcp@0.3.10)

Khwan, an AI memory tool that lets agents recall distilled facts across sessions, released version 0.3.10 to the official MCP registry on 2026-08-26, distributed as khwan-mcp on PyPI and as a hosted remote over streamable-http. The tool, filed under Memory & RAG, declares 4 environment variables including KHWAN_API_KEY and KHWAN_CORE, and supports free and paid plans with limits such as 3 users on the free plan. The mcpindex gate pins Khwan's tool contracts to prevent silent drift, though the tool has not yet received a clearing verdict from the index's evaluation.

← Index /leaderboard Khwan Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones. The current version, v0.3.10, was published to the official MCP registry on 2026-08-26. It is distributed as khwan-mcp on PyPI and as a hosted remote over streamable-http, filed under Memory & RAG 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 Khwan 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 Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands 15/150 labels to graduation . The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits /methodology . Own this server? Screen its description → /screen That verdict was true at screening time snapshot 2026-08-26 . Contracts can change after screening, with no version bump. The gate pins Khwan’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 KHWAN API KEY Your Khwan key from https://app.khwan.ai kwk live ... . It authenticates you to Khwan; it is not your model provider's key. KHWAN CORE Select a named core brain . Paid plans only — the free plan has just default , and an unknown slug answers 404. Leave unset to use the default. KHWAN USER A separate brain inside the core, created on first write — 3 on the free plan, unlimited on paid. Sets the X-Khwan-User header. KHWAN BASE URL Override the API base URL, e.g. http://127.0.0.1:8010 for a self-hosted engine. methodology /methodology Fodda Knowledge Graphsai.fodda/mcp-server /server/ai-fodda-mcp-server Expert-curated knowledge, brand, research & earnings intelligence — 47 tools, 220+ graphs. Achriomcom.achriom/achriom /server/com-achriom-achriom Media memory for AI agents and their humans: books, movies, music, shows, anime, podcasts, games. Kumbukaai.kumbuka/kumbuka-server /server/ai-kumbuka-kumbuka-server Governed, auditable knowledge your team curates for its AI assistants, self-hostable