{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_kepq6k3uvwgg","handle":"recall-mcp","url":"https://wellknown.network/agents/recall-mcp","links":{"self":"https://wellknown.network/agents/recall-mcp/record.json","html":"https://wellknown.network/agents/recall-mcp","markdown":"https://wellknown.network/agents/recall-mcp/record.md","api":"https://wellknown.network/api/v1/agents/recall-mcp","status":"https://wellknown.network/api/v1/agents/recall-mcp/status","claim":"https://wellknown.network/agents/recall-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/recall-mcp/claim.json","badge":"https://wellknown.network/agents/recall-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:recall-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"recall-mcp","summary":"Shared persistent memory for Claude Code, Gemini CLI, Cursor, and any MCP-aware AI client. Local-first, brain-swappable.","description":"# recall-mcp\n\n> **One shared, layered, local-first brain for every AI CLI you use.**\n> Claude Code, Gemini CLI, Cursor, Continue, Zed — they all forget. recall-mcp is the memory they share.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Python 3.10+](https://img.shields.io/badge/Python-3.10+-blue.svg)](https://www.python.org)\n[![MCP](https://img.shields.io/badge/protocol-MCP-a371f7.svg)](https://modelcontextprotocol.io)\n[![Local-first](https://img.shields.io/badge/storage-local--first-orange.svg)](#storage-location)\n\n## Quick start\n\n```bash\n# Install\npipx install recall-mcp\n\n# Wire it into Claude Code (one-time)\necho '{\"mcpServers\":{\"recall-mcp\":{\"type\":\"stdio\",\"command\":\"recall-mcp\"}}}' >> ~/.claude.json\n\n# Restart Claude Code. Done.\n```\n\nThat's it. Every conversation now writes to and reads from the same persistent brain — and so do Gemini CLI, Cursor, and any other MCP-aware client you wire up the same way.\n\n## What it does\n\n```mermaid\nflowchart TD\n    A[Claude Code] -- MCP --> M[recall-mcp]\n    B[Gemini CLI] -- MCP --> M\n    C[Cursor / Continue / Zed] -- MCP --> M\n    M --> S[(SQLite<br/>facts)]\n    M --> V[(ChromaDB<br/>vectors)]\n    M --> E[(Entity<br/>graph)]\n    M --> T[(Temporal<br/>lineage)]\n    M --> F[(FTS5<br/>keyword)]\n    classDef client fill:#1f6feb,stroke:#1f6feb,color:#fff,stroke-width:0\n    classDef brain fill:#a371f7,stroke:#a371f7,color:#fff,stroke-width:0\n    classDef store fill:#0d1117,stroke:#30363d,color:#7d8590\n    class A,B,C client\n    class M brain\n    class S,V,E,T,F store\n```\n\nEvery AI CLI has the same blind spot: each new session starts with amnesia. Native `save_memory` tools store flat lists that bloat the system prompt over time. Cloud memory services need accounts, paid tiers, and trust your data to a vendor.\n\n**recall-mcp gives you one brain shared by every MCP-aware AI client:**\n\n- 🧠 **7 memory layers** — vector similarity, BM25 keyword, entity graph, temporal lineage, importance scoring, fo…","publisher":{"name":"Dhari Alqahtani","url":null},"homepage":"https://github.com/Dhari-Q/recall-mcp","repository":"https://github.com/Dhari-Q/recall-mcp","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp","model-context-protocol","ai","memory","claude","gemini","cursor","agent","rag"],"pricing":null,"endpoints":[{"url":"pypi:recall-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"}],"categories":["data","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"recall-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:13.883Z","publishedAt":"2026-04-28T05:45:54.885609Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"recall-mcp","url":"https://pypi.org/project/recall-mcp/","firstSeenAt":"2026-09-10T11:26:15.775Z","fetchedAt":"2026-09-10T11:26:15.775Z","normalizedAt":"2026-09-10T11:26:15.775Z"}]},"firstSeenAt":"2026-09-10T11:26:15.775Z","updatedAt":"2026-09-10T11:28:13.883Z"}