{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ujhv2xcnmcf4","handle":"mcp-context-graph","url":"https://wellknown.network/agents/mcp-context-graph","links":{"self":"https://wellknown.network/agents/mcp-context-graph/record.json","html":"https://wellknown.network/agents/mcp-context-graph","markdown":"https://wellknown.network/agents/mcp-context-graph/record.md","api":"https://wellknown.network/api/v1/agents/mcp-context-graph","status":"https://wellknown.network/api/v1/agents/mcp-context-graph/status","claim":"https://wellknown.network/agents/mcp-context-graph/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-context-graph/claim.json","badge":"https://wellknown.network/agents/mcp-context-graph/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-context-graph/history","tools":"https://wellknown.network/api/v1/agents/mcp-context-graph/tools"},"ard":{"identifier":"urn:air::server:mcp-context-graph","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-context-graph","summary":"A zero-dependency, in-memory graph database providing a memory layer for local AI agents with AST-based dependency tracking and Token-Level Provenance via Source Maps.","description":"# MCP Context Graph\n\nA self-contained, in-memory graph database for AI Agents. Provides semantic code understanding through the Model Context Protocol (MCP).\n\n## Why This Tool?\n\nAI coding assistants often struggle with large codebases. They either:\n- Read entire files (expensive, hits context limits)\n- Grep for text (misses semantic relationships)\n- Lose track of where functions are called from\n\n**MCP Context Graph solves this by building a semantic graph of your codebase** that the AI can query efficiently.\n\n### Key Differentiators\n\n| Feature | Benefit |\n|---------|---------|\n| **Token-Level Source Maps** | Stores minified signatures but can expand to exact original source with character-accurate mapping |\n| **Semantic Call Graph** | \"Who calls this function?\" answered in milliseconds, not by reading every file |\n| **Polyglot Engine** | Python, TypeScript, JavaScript parsed with tree-sitter grammars |\n| **Zero Install** | Run instantly with `uvx` - no pip install, no dependencies to manage |\n| **MCP Native** | Built for AI agents - exposes tools through Model Context Protocol |\n| **Smart Exclusions** | Respects `.gitignore`, skips `node_modules`, `.venv`, `__pycache__` automatically |\n| **Lazy Ingestion** | Files indexed on-demand, auto-refreshed when modified |\n\n### How It Works\n\n```\nYour Codebase                    MCP Context Graph                AI Agent\n     |                                  |                              |\n     |  ──── tree-sitter parse ────>    |                              |\n     |                                  |                              |\n     |  <── minified signatures ────    |                              |\n     |      + source maps               |                              |\n     |                                  |                              |\n     |                                  |  <── find_callers(\"fn\") ──   |\n     |                                  |  ──> [caller1, caller2] ───> |\n     |                           …","publisher":{"name":"MCP Context Graph Team","url":null},"homepage":null,"repository":null,"version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["ai-agents","ast","context","graph","mcp","tree-sitter"],"pricing":null,"endpoints":[{"url":"pypi:mcp-context-graph","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"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"}],"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-context-graph","registry":"pypi","observedAt":"2026-10-28T10:24:31.058Z","publishedAt":"2026-01-31T20:08:41.952076Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-context-graph","url":"https://pypi.org/project/mcp-context-graph/","firstSeenAt":"2026-09-10T01:19:32.965Z","fetchedAt":"2026-10-28T10:23:38.498Z","normalizedAt":"2026-10-28T10:23:38.498Z"}]},"firstSeenAt":"2026-09-10T01:19:32.965Z","updatedAt":"2026-10-28T10:24:31.058Z"}