{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_8k7659a6an5b","handle":"mcp-kg-skills","url":"https://wellknown.network/agents/mcp-kg-skills","links":{"self":"https://wellknown.network/agents/mcp-kg-skills/record.json","html":"https://wellknown.network/agents/mcp-kg-skills","markdown":"https://wellknown.network/agents/mcp-kg-skills/record.md","api":"https://wellknown.network/api/v1/agents/mcp-kg-skills","status":"https://wellknown.network/api/v1/agents/mcp-kg-skills/status","claim":"https://wellknown.network/agents/mcp-kg-skills/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-kg-skills/claim.json","badge":"https://wellknown.network/agents/mcp-kg-skills/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-kg-skills/history","tools":"https://wellknown.network/api/v1/agents/mcp-kg-skills/tools"},"ard":{"identifier":"urn:air::server:mcp-kg-skills","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-kg-skills","summary":"A Model Context Protocol server for managing a graph of reusable Python functions, documentation, and environment variables","description":"# MCP Knowledge Graph Skills\n\nA Model Context Protocol (MCP) server that manages a graph of reusable Python functions, documentation, and environment variables. Claude can dynamically compose and execute scripts by importing functions from the graph.\n\n## Features\n\n- **Graph-Based Knowledge Management**: Organize skills, scripts, documentation, and environments in a Neo4j knowledge graph\n- **Dynamic Script Composition**: Import and combine Python functions at execution time\n- **Automatic Dependency Management**: PEP 723 inline script metadata with uv-powered execution\n- **Secret Protection**: Automatic detection and sanitization of sensitive environment variables\n- **Relationship Tracking**: Connect related skills and resources with CONTAINS and RELATE_TO relationships\n- **Flexible Querying**: Explore the knowledge graph using read-only Cypher queries\n\n## Quick Start\n\nGet started in 3 steps:\n\n```bash\n# 1. Install uv (if not already installed)\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# 2. Start Neo4j (using Docker)\ndocker run -d --name neo4j -p 7687:7687 -e NEO4J_AUTH=neo4j/password neo4j:latest\n\n# 3. Create config file\nmkdir -p ~/.mcp-kg-skills/config\ncat > ~/.mcp-kg-skills/config/database.yaml << 'EOF'\ndatabase:\n  uri: \"bolt://localhost:7687\"\n  username: \"neo4j\"\n  password: \"password\"\n  database: \"neo4j\"\nexecution:\n  cache_dir: \"~/.mcp-kg-skills/cache\"\n  env_dir: \"~/.mcp-kg-skills/envs\"\n  default_timeout: 300\n  max_timeout: 600\nsecurity:\n  secret_patterns:\n    - \"^SECRET_\"\n    - \"_SECRET$\"\n    - \"^.*_KEY$\"\n    - \"^.*_PASSWORD$\"\n    - \"^.*_TOKEN$\"\nlogging:\n  level: \"INFO\"\nEOF\n\n# 4. Run the server\nuvx mcp-kg-skills\n```\n\nThat's it! Now configure your MCP client (see [MCP Client Configuration](#mcp-client-configuration)).\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────┐\n│         LLM (Claude via MCP Client)                 │\n└─────────────────┬───────────────────────────────────┘\n                  │ MCP Protocol (FastMCP 2.10)\n┌────…","publisher":{"name":"MCP KG Skills Team","url":null},"homepage":null,"repository":null,"version":"0.1.3","license":"MIT","protocols":["mcp"],"tags":["fastmcp","knowledge-graph","mcp","model-context-protocol","neo4j"],"pricing":null,"endpoints":[{"url":"pypi:mcp-kg-skills","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"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-kg-skills","registry":"pypi","observedAt":"2026-10-28T11:27:30.202Z","publishedAt":"2025-11-26T21:25:12.687219Z","latestVersion":"0.1.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-kg-skills","url":"https://pypi.org/project/mcp-kg-skills/","firstSeenAt":"2026-09-10T02:23:09.746Z","fetchedAt":"2026-10-28T11:26:58.919Z","normalizedAt":"2026-10-28T11:26:58.919Z"}]},"firstSeenAt":"2026-09-10T02:23:09.746Z","updatedAt":"2026-10-28T11:27:30.202Z"}