{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_98yrc7jbps89","handle":"agent-brain-ag-mcp","url":"https://wellknown.network/agents/agent-brain-ag-mcp","links":{"self":"https://wellknown.network/agents/agent-brain-ag-mcp/record.json","html":"https://wellknown.network/agents/agent-brain-ag-mcp","markdown":"https://wellknown.network/agents/agent-brain-ag-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agent-brain-ag-mcp","status":"https://wellknown.network/api/v1/agents/agent-brain-ag-mcp/status","claim":"https://wellknown.network/agents/agent-brain-ag-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-brain-ag-mcp/claim.json","badge":"https://wellknown.network/agents/agent-brain-ag-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:agent-brain-ag-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agent-brain-ag-mcp","summary":"Agent Brain MCP - Model Context Protocol server exposing Agent Brain as MCP tools, resources, and prompts","description":"# agent-brain-mcp\n\nModel Context Protocol server for [Agent Brain](https://github.com/SpillwaveSolutions/agent-brain).\n\nExposes the running Agent Brain instance as an MCP server consumable by Claude Desktop, Cursor, Windsurf, Claude Agent SDK, LangChain DeepAgents, and any other MCP-aware client.\n\n## Surface (v10.4)\n\n- **16 Tools**: `search_documents`, `query_count`, `explain_result`, `index_folder`, `add_documents`, `inject_documents`, `get_job`, `list_jobs`, `wait_for_job`, `cancel_job`, `list_folders`, `remove_folder`, `cache_status`, `clear_cache`, `list_file_types`, `server_health`\n- **5 Resources** (read-only): `corpus://config`, `corpus://status`, `corpus://health`, `corpus://providers`, `corpus://folders`\n- **6 Prompts**: `find-callers`, `find-implementation`, `explain-architecture`, `compare-search-modes`, `onboard-to-codebase`, `audit-indexed-folders`\n- **Listen transport**: stdio (default) or Streamable HTTP (`--transport http`)\n- **Backend**: UDS (preferred) or HTTP, selectable via `--backend {auto,uds,http}`\n- **Auth**: OAuth 2.1 on the HTTP listen transport (`AGENT_BRAIN_AUTH=oauth`), **off by default**\n\nThe full v1–v4 MCP roadmap shipped by Agent Brain 10.4.0; see [`CHANGELOG.md`](../docs/CHANGELOG.md)\nand the [MCP User Guide](../docs/MCP_USER_GUIDE.md). Register for Claude Code with\n`agent-brain install-agent --agent claude --with-mcp`.\n\n## Install\n\n```bash\npip install agent-brain-ag-mcp\n```\n\nThe PyPI distribution is `agent-brain-ag-mcp`; the installed console script is `agent-brain-mcp`.\n\n## Quick config\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-brain\": {\n      \"command\": \"agent-brain-mcp\",\n      \"args\": [\"--backend\", \"auto\"],\n      \"env\": { \"AGENT_BRAIN_STATE_DIR\": \"/abs/path/.agent-brain\" }\n    }\n  }\n}\n```\n\n## Transport selection (v10.2+)\n\n`agent-brain-mcp` supports two **listen transports** for talking to MCP clients:\n\n- **stdio** (default) — Claude Desktop, Claude Code, and most MCP CLI clients use this. No flags needed.\n- **http** (Streamable HT…","publisher":{"name":"Spillwave Solutions","url":null},"homepage":"https://github.com/SpillwaveSolutions/agent-brain","repository":"https://github.com/SpillwaveSolutions/agent-brain/wiki","version":"10.7.0","license":"MIT","protocols":["mcp"],"tags":["agent-brain","mcp","model-context-protocol","rag","claude","claude-desktop"],"pricing":null,"endpoints":[{"url":"pypi:agent-brain-ag-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":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"ai.prompting","name":"Prompt Management","confidence":0.791,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.745,"provenance":"derived"}],"categories":["ai","data","security"],"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":"agent-brain-ag-mcp","registry":"pypi","observedAt":"2026-09-09T08:22:26.460Z","publishedAt":"2026-09-03T19:55:43.432821Z","latestVersion":"10.7.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agent-brain-ag-mcp","url":"https://pypi.org/project/agent-brain-ag-mcp/","firstSeenAt":"2026-09-09T08:20:44.868Z","fetchedAt":"2026-09-09T08:20:44.868Z","normalizedAt":"2026-09-09T08:20:44.868Z"}]},"firstSeenAt":"2026-09-09T08:20:44.868Z","updatedAt":"2026-09-09T08:22:26.460Z"}