{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hdrxqr9635xq","handle":"mcp-knowledge-graph","url":"https://wellknown.network/agents/mcp-knowledge-graph","links":{"self":"https://wellknown.network/agents/mcp-knowledge-graph/record.json","html":"https://wellknown.network/agents/mcp-knowledge-graph","markdown":"https://wellknown.network/agents/mcp-knowledge-graph/record.md","api":"https://wellknown.network/api/v1/agents/mcp-knowledge-graph","status":"https://wellknown.network/api/v1/agents/mcp-knowledge-graph/status","claim":"https://wellknown.network/agents/mcp-knowledge-graph/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-knowledge-graph/claim.json","badge":"https://wellknown.network/agents/mcp-knowledge-graph/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-knowledge-graph/history","tools":"https://wellknown.network/api/v1/agents/mcp-knowledge-graph/tools"},"ard":{"identifier":"urn:air::server:mcp-knowledge-graph","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-knowledge-graph","summary":"Neo4j knowledge graph retrieval MCP server","description":"# Neo4j Knowledge Graph MCP Server\n\nMCP server for enterprise knowledge graph retrieval over Neo4j. Client LLM generates Cypher; this server provides schema resources, validation, and read-only execution.\n\n> 中文详细说明请参阅：[docs/知识图谱检索MCP服务说明.md](docs/知识图谱检索MCP服务说明.md)\n\n## Architecture\n\n- **10 Resources**: 7 static (schema, constraints, conventions, semantics, glossary, patterns, safety) + 3 dynamic (stats, samples, indexes)\n- **7 Tools**: `get_graph_context`, `get_cypher_prompt`, `validate_cypher`, `execute_cypher`, `explain_cypher`, `resolve_entity`, `refresh_graph_stats`\n- **4 Prompts**: `generate_cypher_query`, `refine_cypher_query`, `explain_query_result`, `decompose_complex_question`\n\nContext Tools (`get_graph_context_tool`, `get_cypher_prompt_tool`) provide the same schema context as Resources/Prompts for **Tools-only** MCP clients that do not support `resources/read` or `prompts/get`.\n\n## Setup\n\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\npip install mcp neo4j pyyaml pydantic pydantic-settings\n```\n\nEnvironment variables:\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `NEO4J_URI` | `bolt://localhost:7687` | Neo4j Bolt URI |\n| `NEO4J_USER` | `neo4j` | Neo4j user |\n| `NEO4J_PASSWORD` | `password` | Neo4j password |\n| `NEO4J_DATABASE` | `neo4j` | Neo4j database |\n| `MCP_TRANSPORT` | `stdio` | `stdio` \\| `streamable-http` \\| `sse` |\n| `MCP_HOST` | `127.0.0.1` | HTTP/SSE bind host |\n| `MCP_PORT` | `8000` | HTTP/SSE bind port |\n| `MCP_SSE_PATH` | `/sse` | SSE endpoint path |\n| `MCP_STREAMABLE_HTTP_PATH` | `/mcp` | Streamable HTTP endpoint path |\n\nCopy `.env.example` to `.env` and adjust as needed.\n\n## Import graph data\n\nFrom ontology_system:\n\n```bash\ncurl -o graph-import.cypher http://localhost:8183/graph/export/cypher\ncypher-shell -u neo4j -p password -f graph-import.cypher\n```\n\n## Run MCP server\n\n### stdio（默认，Cursor 子进程模式）\n\n```bash\nPYTHONPATH=. python -m src.server\n```\n\n### streamable-http（推荐 HTTP 模式）\n\n```bash\nPYTHONPATH=. py…","publisher":null,"homepage":null,"repository":null,"version":"0.1.2","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-knowledge-graph","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.745,"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":"mcp-knowledge-graph","registry":"pypi","observedAt":"2026-10-28T11:27:30.628Z","publishedAt":"2026-07-06T09:39:53.237289Z","latestVersion":"0.1.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-knowledge-graph","url":"https://pypi.org/project/mcp-knowledge-graph/","firstSeenAt":"2026-09-10T02:23:12.009Z","fetchedAt":"2026-10-28T11:27:01.300Z","normalizedAt":"2026-10-28T11:27:01.300Z"}]},"firstSeenAt":"2026-09-10T02:23:12.009Z","updatedAt":"2026-10-28T11:27:30.628Z"}