{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xh6bdvvbfybm","handle":"knowledge-graph-rag-mcp","url":"https://wellknown.network/agents/knowledge-graph-rag-mcp","links":{"self":"https://wellknown.network/agents/knowledge-graph-rag-mcp/record.json","html":"https://wellknown.network/agents/knowledge-graph-rag-mcp","markdown":"https://wellknown.network/agents/knowledge-graph-rag-mcp/record.md","api":"https://wellknown.network/api/v1/agents/knowledge-graph-rag-mcp","status":"https://wellknown.network/api/v1/agents/knowledge-graph-rag-mcp/status","claim":"https://wellknown.network/agents/knowledge-graph-rag-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/knowledge-graph-rag-mcp/claim.json","badge":"https://wellknown.network/agents/knowledge-graph-rag-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/knowledge-graph-rag-mcp/history","tools":"https://wellknown.network/api/v1/agents/knowledge-graph-rag-mcp/tools"},"ard":{"identifier":"urn:air::server:knowledge-graph-rag-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"knowledge-graph-rag-mcp","summary":"Local-first Knowledge GraphRAG MCP server","description":"# Knowledge GraphRAG MCP Server\n\nA local-first **Model Context Protocol (MCP)** server that watches a knowledge repository, extracts entities and relations, embeds content with EmbeddingGemma, and serves hybrid (graph + vector) retrieval tools to MCP clients.\n\n- **Local pipeline:** directory watcher → normalization → chunking → entity & relation extraction → sqlite-vec vectorization → graph storage\n- **Knowledge graph:** canonical entities, mentions, and typed relations navigated via the bundled `bfsvtab` breadth-first search extension\n- **Hybrid retrieval:** semantic vector prefiltering paired with graph expansion and provenance-rich responses\n\nAll native dependencies ship with the Python package—no external services or manual compilation required.\n\n## Feature Overview\n\n| Area | Highlights |\n| --- | --- |\n| Document ingestion | Markdown/HTML/txt normalization, deduplication, preludes for provenance |\n| Entity understanding | Mention extraction, canonical linking, relation inference (`uses`, `depends_on`, `defines`, `cites`, …) |\n| Storage | SQLite with WAL, `sqlite-vec` for vectors, `bfsvtab` for graph traversal |\n| Retrieval tools | Vector + graph search, entity lookup/explain, ingestion/refresh controls, status reporting |\n| Local-first | EmbeddingGemma model runs locally (or via optional remote endpoint) |\n\n## Quick Start with `uvx`\n\nThe published wheel already includes the native SQLite extensions. You can run the CLI without cloning the repository:\n\n```bash\n# Inspect available commands\nuvx knowledge-graphrag-mcp --help\n\n# Initialize the database and report status\nuvx knowledge-graphrag-mcp status --config config.yaml\n\n# Ingest Markdown files inside a knowledge directory\nuvx knowledge-graphrag-mcp ingest ./knowledge/**/*.md --config config.yaml\n\n# Issue a hybrid retrieval query\nuvx knowledge-graphrag-mcp hybrid-query \"data retention policy\" --config config.yaml\n```\n\n### Minimal configuration (`config.yaml`)\n\n```yaml\nproject: \"knowledge-graphrag\"\nsqlite:\n  path…","publisher":{"name":"Knowledge GraphRAG Team","url":null},"homepage":"https://github.com/anthropic-ai/knowledge-graph-rag-mcp","repository":"https://github.com/anthropic-ai/knowledge-graph-rag-mcp","version":"0.1.2","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:knowledge-graph-rag-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.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.859,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"}],"categories":["data","dev","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":"knowledge-graph-rag-mcp","registry":"pypi","observedAt":"2026-10-28T08:28:08.387Z","publishedAt":"2025-10-14T22:45:04.100068Z","latestVersion":"0.1.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"knowledge-graph-rag-mcp","url":"https://pypi.org/project/knowledge-graph-rag-mcp/","firstSeenAt":"2026-09-09T22:23:39.026Z","fetchedAt":"2026-10-28T08:26:49.862Z","normalizedAt":"2026-10-28T08:26:49.862Z"}]},"firstSeenAt":"2026-09-09T22:23:39.026Z","updatedAt":"2026-10-28T08:28:08.387Z"}