{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_7tpyhkj85zzf","handle":"skill-graph-mcp","url":"https://wellknown.network/agents/skill-graph-mcp","links":{"self":"https://wellknown.network/agents/skill-graph-mcp/record.json","html":"https://wellknown.network/agents/skill-graph-mcp","markdown":"https://wellknown.network/agents/skill-graph-mcp/record.md","api":"https://wellknown.network/api/v1/agents/skill-graph-mcp","status":"https://wellknown.network/api/v1/agents/skill-graph-mcp/status","claim":"https://wellknown.network/agents/skill-graph-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/skill-graph-mcp/claim.json","badge":"https://wellknown.network/agents/skill-graph-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:skill-graph-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"skill-graph-mcp","summary":"Knowledge graph + vector search for AI agent skill discovery","description":"# Skill Graph\n\n**Knowledge graph + vector search for AI agent skill discovery.**\n\nYour agent doesn't need to read 500 skill files to find the 3 that matter. Skill Graph indexes `[[wikilink]]`-connected markdown into a traversable graph, then serves it over MCP so agents navigate knowledge structures instead of loading everything into context.\n\n```\nsearch → descriptions → links → sections → full content\nMost decisions happen before reading a single full file.\n```\n\n## Why\n\nAI agents discover skills by dumping every description into the prompt. 50 skills? Fine. 500? You're burning tokens and diluting attention on content the agent will never use.\n\nSkill Graph fixes this with **progressive disclosure** — the agent sees only what's relevant, follows links when curious, and loads full content only when it's time to act. In real-world testing, this saves **97-98% of tokens** compared to the \"load everything\" approach.\n\nThe graph comes from `[[wikilinks]]` already in your prose. No schema to design, no config to write. If your notes link to each other, you already have a skill graph.\n\n## Install\n\n```bash\npip install skill-graph-mcp\n```\n\nOr run without installing:\n\n```bash\nuvx skill-graph-mcp --help\n```\n\n## Quick Start\n\n```bash\n# Index a directory of markdown files\nskill-graph index ~/my-skills/\n\n# Search (hybrid vector + graph)\nskill-graph search \"deploy to production\"\n\n# Browse\nskill-graph list --limit 20\nskill-graph list --category devops\n\n# Graph overview\nskill-graph stats\n\n# Start MCP server for agent use\nskill-graph serve\n```\n\n## Use with AI Agents (MCP)\n\nAdd to your Claude Code `.mcp.json`, Cursor config, or any MCP-compatible agent:\n\n```json\n{\n  \"mcpServers\": {\n    \"skill-graph\": {\n      \"command\": \"uvx\",\n      \"args\": [\"skill-graph-mcp\", \"serve\"]\n    }\n  }\n}\n```\n\nThe agent gets 7 tools for progressive disclosure:\n\n| Tool | What it does |\n|------|-------------|\n| `search_skills(query)` | Semantic + graph search — returns descriptions only |\n| `get_skill(name)` | Sha…","publisher":{"name":"Julian Saks","url":null},"homepage":"https://github.com/kingjulio8238/skill_graph","repository":"https://github.com/kingjulio8238/skill_graph","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["ai-agents","knowledge-graph","mcp","skill-discovery","vector-search","wikilinks"],"pricing":null,"endpoints":[{"url":"pypi:skill-graph-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"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"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"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":"skill-graph-mcp","registry":"pypi","observedAt":"2026-09-10T12:23:32.433Z","publishedAt":"2026-03-13T08:26:12.212629Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"skill-graph-mcp","url":"https://pypi.org/project/skill-graph-mcp/","firstSeenAt":"2026-09-10T12:22:22.654Z","fetchedAt":"2026-09-10T12:22:22.654Z","normalizedAt":"2026-09-10T12:22:22.654Z"}]},"firstSeenAt":"2026-09-10T12:22:22.654Z","updatedAt":"2026-09-10T12:23:32.433Z"}