{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_sdvf2tjhbc97","handle":"mcp-neo4j-graphrag","url":"https://wellknown.network/agents/mcp-neo4j-graphrag","links":{"self":"https://wellknown.network/agents/mcp-neo4j-graphrag/record.json","html":"https://wellknown.network/agents/mcp-neo4j-graphrag","markdown":"https://wellknown.network/agents/mcp-neo4j-graphrag/record.md","api":"https://wellknown.network/api/v1/agents/mcp-neo4j-graphrag","status":"https://wellknown.network/api/v1/agents/mcp-neo4j-graphrag/status","claim":"https://wellknown.network/agents/mcp-neo4j-graphrag/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-neo4j-graphrag/claim.json","badge":"https://wellknown.network/agents/mcp-neo4j-graphrag/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-neo4j-graphrag/history","tools":"https://wellknown.network/api/v1/agents/mcp-neo4j-graphrag/tools"},"ard":{"identifier":"urn:air::server:mcp-neo4j-graphrag","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-neo4j-graphrag","summary":"A unified Neo4j MCP server for GraphRAG: vector search, fulltext search, search-augmented Cypher queries, write operations, and multimodal image retrieval","description":"# Neo4j GraphRAG MCP Server\n\n[![PyPI version](https://badge.fury.io/py/mcp-neo4j-graphrag.svg)](https://pypi.org/project/mcp-neo4j-graphrag/)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nAn MCP server that extends Neo4j with **vector search**, **fulltext search**, **search-augmented Cypher queries**, **write operations**, and **multimodal image retrieval** for GraphRAG applications.\n\n> **Inspired by** the [Neo4j Labs `mcp-neo4j-cypher`](https://github.com/neo4j-contrib/mcp-neo4j/tree/main/servers/mcp-neo4j-cypher) server. This server adds vector search, fulltext search, and the innovative `search_cypher_query` tool for combining search with graph traversal.\n\n## Overview\n\nThis server enables LLMs to:\n- 🔍 Search Neo4j vector indexes using semantic similarity\n- 📝 Search fulltext indexes with Lucene syntax\n- ⚡ Combine search with Cypher queries via `search_cypher_query`\n- 🕸️ Execute read-only Cypher queries\n- ✏️ Execute write Cypher queries (CREATE, MERGE, SET, DELETE)\n- 🖼️ Retrieve images stored in Neo4j nodes (multimodal — returns the image directly to the LLM)\n\nBuilt on [LiteLLM](https://docs.litellm.ai/) for multi-provider embedding support (OpenAI, Azure, Bedrock, Cohere, etc.).\n\n> **Related:** For the official Neo4j MCP Server, see [neo4j/mcp](https://github.com/neo4j/mcp). For Neo4j Labs MCP Servers (Cypher, Memory, Data Modeling), see [neo4j-contrib/mcp-neo4j](https://github.com/neo4j-contrib/mcp-neo4j).\n\n## Installation\n\n```bash\n# Using pip\npip install mcp-neo4j-graphrag\n\n# Using uv (recommended)\nuv pip install mcp-neo4j-graphrag\n```\n\n## Configuration\n\n### Claude Desktop\n\nEdit the configuration file:\n- **macOS/Linux:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"neo4j-graphra…","publisher":{"name":"Jean-Marc Guerin","url":null},"homepage":"https://github.com/guerinjeanmarc/mcp-neo4j-graphrag","repository":"https://github.com/guerinjeanmarc/mcp-neo4j-graphrag","version":"0.4.2","license":"MIT","protocols":["mcp"],"tags":["embeddings","graphrag","knowledge-graph","llm","mcp","neo4j","rag","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:mcp-neo4j-graphrag","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":"knowledge.knowledge-graph","name":"Knowledge Graphs","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":"mcp-neo4j-graphrag","registry":"pypi","observedAt":"2026-10-28T12:22:53.094Z","publishedAt":"2026-07-17T09:29:40.788345Z","latestVersion":"0.4.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-neo4j-graphrag","url":"https://pypi.org/project/mcp-neo4j-graphrag/","firstSeenAt":"2026-09-10T02:24:07.621Z","fetchedAt":"2026-10-28T12:21:17.281Z","normalizedAt":"2026-10-28T12:21:17.281Z"}]},"firstSeenAt":"2026-09-10T02:24:07.621Z","updatedAt":"2026-10-28T12:22:53.094Z"}