{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_rcmwwajsse3n","handle":"mcp-graph-engine","url":"https://wellknown.network/agents/mcp-graph-engine","links":{"self":"https://wellknown.network/agents/mcp-graph-engine/record.json","html":"https://wellknown.network/agents/mcp-graph-engine","markdown":"https://wellknown.network/agents/mcp-graph-engine/record.md","api":"https://wellknown.network/api/v1/agents/mcp-graph-engine","status":"https://wellknown.network/api/v1/agents/mcp-graph-engine/status","claim":"https://wellknown.network/agents/mcp-graph-engine/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-graph-engine/claim.json","badge":"https://wellknown.network/agents/mcp-graph-engine/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-graph-engine/history","tools":"https://wellknown.network/api/v1/agents/mcp-graph-engine/tools"},"ard":{"identifier":"urn:air::server:mcp-graph-engine","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-graph-engine","summary":"A graph database and analysis tool for AI assistants via MCP","description":"# MCP Graph Engine\n\nA graph database for AI assistants via the Model Context Protocol. Build relationship graphs, run analysis algorithms, and visualize in real-time.\n\n<img alt=\"image\" src=\"docs/assets/screenshot.png\" />\n\n## Installation\n\n**Requirements:** Python 3.10+, MCP-compatible client (Claude Code, Claude Desktop, Cursor)\n\n```bash\npipx install mcp-graph-engine\n```\n\nAdd to your MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"graph-engine\": {\n      \"command\": \"mcp-graph-engine\"\n    }\n  }\n}\n```\n\n| Client | Config Location |\n|--------|-----------------|\n| Claude Code | `~/.mcp.json` or `.mcp.json` |\n| Claude Desktop | `~/Library/Application Support/Claude/claude_desktop_config.json` |\n| Cursor | `.cursor/mcp.json` |\n\nRestart your client after adding the config.\n\n## What You Can Do\n\nJust ask your AI assistant:\n\n- \"Map out the dependencies in this codebase\"\n- \"Build a graph of the characters in this document\"\n- \"What's the most critical component?\"\n- \"Are there any circular dependencies?\"\n- \"Show me the path from X to Y\"\n- \"Visualize the graph\"\n\nThe AI handles the tool calls. You get a live visualization at `http://localhost:8765`.\n\n## Features\n\n- **Analysis** - PageRank, cycle detection, shortest paths, connected components\n- **Visualization** - Live D3 force-directed graph in your browser\n- **Import/Export** - DOT, CSV, GraphML, JSON, Mermaid\n\n## Configuration\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `VIS_PORT` | `8765` | Visualization server port |\n| `VIS_HOST` | `localhost` | Visualization server host |\n| `VIS_ENABLED` | `true` | Enable/disable visualization |\n\n## Notes\n\n- **Transient** - Graphs live in memory. Export to JSON for persistence.\n- **Fuzzy matching** - `pipx install mcp-graph-engine[embeddings]` for semantic node matching.\n\n## License\n\nMIT","publisher":{"name":"utilitydelta","url":null},"homepage":"https://github.com/utilitydelta/mcp-graph-engine#readme","repository":"https://github.com/utilitydelta/mcp-graph-engine/blob/main/CHANGELOG.md","version":"1.0.1","license":"MIT","protocols":["mcp"],"tags":["mcp","graph","knowledge-graph","llm","ai-assistant","networkx","cypher"],"pricing":null,"endpoints":[{"url":"pypi:mcp-graph-engine","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":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"}],"categories":["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-graph-engine","registry":"pypi","observedAt":"2026-10-28T11:27:21.869Z","publishedAt":"2026-01-30T22:32:09.856560Z","latestVersion":"1.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-graph-engine","url":"https://pypi.org/project/mcp-graph-engine/","firstSeenAt":"2026-09-10T01:21:27.969Z","fetchedAt":"2026-10-28T11:26:17.108Z","normalizedAt":"2026-10-28T11:26:17.108Z"}]},"firstSeenAt":"2026-09-10T01:21:27.969Z","updatedAt":"2026-10-28T11:27:21.869Z"}