Local-first Knowledge GraphRAG MCP server
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"knowledge-graph-rag-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Knowledge GraphRAG MCP Server A 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. - **Local pipeline:** directory watcher → normalization → chunking → entity & relation extraction → sqlite-vec vectorization → graph storage - **Knowledge graph:** canonical entities, mentions, and typed relations navigated via the bundled `bfsvtab` breadth-first search extension - **Hybrid retrieval:** semantic vector prefiltering paired with graph expansion and provenance-rich responses All native dependencies ship with the Python package—no external services or manual compilation required. ## Feature Overview | Area | Highlights | | --- | --- | | Document ingestion | Markdown/HTML/txt normalization, deduplication, preludes for provenance | | Entity understanding | Mention extraction, canonical linking, relation inference (`uses`, `depends_on`, `defines`, `cites`, …) | | Storage | SQLite with WAL, `sqlite-vec` for vectors, `bfsvtab` for graph traversal | | Retrieval tools | Vector + graph search, entity lookup/explain, ingestion/refresh controls, status reporting | | Local-first | EmbeddingGemma model runs locally (or via optional remote endpoint) | ## Quick Start with `uvx` The published wheel already includes the native SQLite extensions. You can run the CLI without cloning the repository: ```bash # Inspect available commands uvx knowledge-graphrag-mcp --help # Initialize the database and report status uvx knowledge-graphrag-mcp status --config config.yaml # Ingest Markdown files inside a knowledge directory uvx knowledge-graphrag-mcp ingest ./knowledge/**/*.md --config config.yaml # Issue a hybrid retrieval query uvx knowledge-graphrag-mcp hybrid-query "data retention policy" --config config.yaml ``` ### Minimal configuration (`config.yaml`) ```yaml project: "knowledge-graphrag" sqlite: path…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.