{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ynekmqxnmnw5","handle":"mcp-fact-finder","url":"https://wellknown.network/agents/mcp-fact-finder","links":{"self":"https://wellknown.network/agents/mcp-fact-finder/record.json","html":"https://wellknown.network/agents/mcp-fact-finder","markdown":"https://wellknown.network/agents/mcp-fact-finder/record.md","api":"https://wellknown.network/api/v1/agents/mcp-fact-finder","status":"https://wellknown.network/api/v1/agents/mcp-fact-finder/status","claim":"https://wellknown.network/agents/mcp-fact-finder/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-fact-finder/claim.json","badge":"https://wellknown.network/agents/mcp-fact-finder/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-fact-finder/history","tools":"https://wellknown.network/api/v1/agents/mcp-fact-finder/tools"},"ard":{"identifier":"urn:air::server:mcp-fact-finder","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-fact-finder","summary":"Semantic fact indexer over markdown knowledge bases — extracts atomic facts, entities, and authority scores, then exposes search via MCP","description":"# mcp-fact-finder\n\nSemantic fact indexer over markdown knowledge bases.\n\nCrawls markdown documents, extracts atomic facts using **local NLP (free, no API key)**\nor an optional LLM enrichment pass, stores facts in LanceDB with authority scoring and\nentity relationships, and exposes structured search via the Model Context Protocol.\n\n---\n\n## Why local inference?\n\n> **Pass 1 (rebel-large NLP) is completely free.**\n\nNo API keys, no rate limits, no cost.  Runs locally on CPU or Apple Silicon MPS\n(Metal Performance Shaders).  A full 7,600-document knowledge base indexes in ~5 hours\nat $0.\n\n**Pass 2 (LLM enrichment) is optional.**  It adds canonical fact forms, tense\nclassification, and better entity linking.  Use a local Ollama instance (free) or\nOpenRouter (~$5–9 for 7,600 docs).\n\n> **Recommendation:** Run Pass 1 first.  For most knowledge bases, Pass 1 alone\n> is sufficient for useful search results.\n\n---\n\n## Status: v0.0.3\n\n| Component             | Status   |\n|-----------------------|----------|\n| Data models           | ✅ Complete |\n| Markdown crawler      | ✅ Complete |\n| Authority scoring     | ✅ Complete |\n| rebel-large extractor | ✅ Complete |\n| Ollama extractor      | ✅ Complete |\n| OpenRouter/Bedrock    | ✅ Complete |\n| Embedder (bge-small)  | ✅ Complete |\n| LanceDB store         | ✅ Complete |\n| MCP server (6 tools)  | ✅ Complete |\n| Inconsistency checker | ✅ Complete |\n| Indexing pipeline     | ✅ Complete |\n| Setup script          | ✅ Complete |\n\n---\n\n## Quick start\n\n### 1. Install\n\n```bash\npip install mcp-fact-finder\n# or\nuv add mcp-fact-finder\n```\n\nOr clone and develop locally:\n\n```bash\ngit clone https://github.com/bobmatnyc/mcp-fact-finder\ncd mcp-fact-finder\nuv sync\n```\n\n### 2. Index your knowledge base (Pass 1 — free, no API key needed)\n\n```bash\n# Index a directory of markdown files\nuv run scripts/index.py --path ~/my-docs/\n\n# First 100 docs only (quick smoke test)\nuv run scripts/index.py --path ~/my-docs/ --limit 100\n\n# Show current stats\nuv run scripts/…","publisher":null,"homepage":"https://github.com/bobmatnyc/mcp-fact-finder","repository":"https://github.com/bobmatnyc/mcp-fact-finder/issues","version":"0.1.3","license":"Copyright (c) 2024-2026 Robert Matsuoka  Elastic License 2.0  U…","protocols":["mcp"],"tags":["entity-resolution","fact-extraction","knowledge-base","lancedb","llm","local-inference","markdown","mcp","semantic-search"],"pricing":null,"endpoints":[{"url":"pypi:mcp-fact-finder","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"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":0.779,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.756,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.75,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.713,"provenance":"derived"}],"categories":["data","dev","documents"],"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-fact-finder","registry":"pypi","observedAt":"2026-10-28T11:27:11.274Z","publishedAt":"2026-03-19T16:17:43.280781Z","latestVersion":"0.1.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-fact-finder","url":"https://pypi.org/project/mcp-fact-finder/","firstSeenAt":"2026-09-10T01:20:35.979Z","fetchedAt":"2026-10-28T11:25:24.615Z","normalizedAt":"2026-10-28T11:25:24.615Z"}]},"firstSeenAt":"2026-09-10T01:20:35.979Z","updatedAt":"2026-10-28T11:27:11.274Z"}