{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2vyzhpfbzqub","handle":"mcp-lightrag","url":"https://wellknown.network/agents/mcp-lightrag","links":{"self":"https://wellknown.network/agents/mcp-lightrag/record.json","html":"https://wellknown.network/agents/mcp-lightrag","markdown":"https://wellknown.network/agents/mcp-lightrag/record.md","api":"https://wellknown.network/api/v1/agents/mcp-lightrag","status":"https://wellknown.network/api/v1/agents/mcp-lightrag/status","claim":"https://wellknown.network/agents/mcp-lightrag/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-lightrag/claim.json","badge":"https://wellknown.network/agents/mcp-lightrag/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-lightrag/history","tools":"https://wellknown.network/api/v1/agents/mcp-lightrag/tools"},"ard":{"identifier":"urn:air::server:mcp-lightrag","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-lightrag","summary":"MCP Server for LightRAG with smart document upsert capabilities","description":"# LightRAG MCP Server\n\nA Model Context Protocol (MCP) server that enables AI assistants to interact with [LightRAG](https://github.com/HKUDS/LightRAG) knowledge graphs. Query documents, manage entities, and build semantic relationships through a standardized tool interface.\n**Optimized for Obsidian Vaults**: The built-in smart upsert and document tracking capabilities make it perfect for agents that need to sync and reason over evolving Obsidian knowledge bases.\n\n## Features\n\n- **Smart Updates**: Intelligent `upsert` logic that detects changes in documents, skipping redundant uploads and re-indexing only when necessary\n- **Knowledge Graph Queries**: Perform semantic, keyword, or hybrid searches across your indexed documents\n- **Document Ingestion**: Add text, files, or entire directories to your knowledge base\n- **Entity Management**: Create, update, merge, and delete entities in the graph\n- **Relationship Handling**: Define and modify connections between entities\n- **Robust Connectivity**: Automatic retry with exponential backoff for reliable API communication\n- **Flexible Configuration**: Set options via environment variables or command-line arguments\n\n## Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/enriquecatala/mcp-lightrag.git\ncd mcp-lightrag\n\n# Install dependencies\nuv sync\n```\n\n## Quick Start\n\n1. **Start your LightRAG server** (must be running before the MCP server)\n\n2. **Launch the MCP server**:\n   ```bash\n   uv run mcp-lightrag --host localhost --port 9621\n   ```\n\n3. **Connect your AI assistant** via the MCP protocol (stdio transport)\n\n## Configuration\n\n| Option        | Environment Variable | Default     | Description       |\n| ------------- | -------------------- | ----------- | ----------------- |\n| `--host`      | `LIGHTRAG_HOST`      | `localhost` | LightRAG API host |\n| `--port`      | `LIGHTRAG_PORT`      | `9621`      | LightRAG API port |\n| `--api-key`   | `LIGHTRAG_API_KEY`   | *(none)*    | Optional API key  |\n| `--lo…","publisher":null,"homepage":"https://enriquecatala.com/","repository":"https://github.com/enriquecatala/mcp-lightrag/issues","version":"0.2.2","license":"MIT","protocols":["mcp"],"tags":["agent","ai","context-protocol","knowledge-graph","lightrag","llm","mcp","obsidian","rag"],"pricing":null,"endpoints":[{"url":"pypi:mcp-lightrag","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"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"productivity.notes","name":"Notes & Docs","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.825,"provenance":"derived"}],"categories":["data","dev","knowledge","productivity"],"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":"mcp-lightrag","registry":"pypi","observedAt":"2026-10-28T12:22:39.566Z","publishedAt":"2026-02-07T23:44:21.574854Z","latestVersion":"0.2.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-lightrag","url":"https://pypi.org/project/mcp-lightrag/","firstSeenAt":"2026-09-10T02:23:19.731Z","fetchedAt":"2026-10-28T12:20:30.609Z","normalizedAt":"2026-10-28T12:20:30.609Z"}]},"firstSeenAt":"2026-09-10T02:23:19.731Z","updatedAt":"2026-10-28T12:22:39.566Z"}