{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xbhxm7t93rbc","handle":"iflow-mcp-yairwein-mcp-doc-indexer","url":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer","links":{"self":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer/record.json","html":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer","markdown":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-yairwein-mcp-doc-indexer","status":"https://wellknown.network/api/v1/agents/iflow-mcp-yairwein-mcp-doc-indexer/status","claim":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-yairwein-mcp-doc-indexer/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-yairwein-mcp-doc-indexer/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-yairwein-mcp-doc-indexer/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-yairwein-mcp-doc-indexer","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_yairwein-mcp-doc-indexer","summary":"MCP server for local document indexing and search using LanceDB","description":"# MCP Document Indexer\n\nA Python-based MCP (Model Context Protocol) server for local document indexing and search using LanceDB vector database and local LLMs.\n\n## Features\n\n- **Real-time Document Monitoring**: Automatically indexes new and modified documents in configured folders\n- **Multi-format Support**: Handles PDF, Word (docx/doc), text, Markdown, and RTF files\n- **Local LLM Integration**: Uses Ollama for document summarization and keyword extraction. Nothing ever leaves your computer\n- **Vector Search**: Semantic search using LanceDB and sentence transformers\n- **MCP Integration**: Exposes search and catalog tools via Model Context Protocol\n- **Incremental Indexing**: Only processes changed files to save resources\n- **Performance Optimized**: Designed for decent performance on standard laptops (e.g. M1/M2 MacBook)\n\n## Installation\n\n### Prerequisites\n\n1. **Python 3.9+** installed\n2. **uv** package manager:\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\n3. **Ollama** (for local LLM):\n```bash\n# Install Ollama\ncurl -fsSL https://ollama.com/install.sh | sh\n\n# Pull a model (e.g., llama3.2)\nollama pull llama3.2:3b\n```\n\n### Install MCP Document Indexer\n\n```bash\n# Clone the repository\ngit clone https://github.com/yairwein/mcp-doc-indexer.git\ncd mcp-doc-indexer\n\n# Install with uv\nuv sync\n\n# Or install as a package\nuv add mcp-doc-indexer\n```\n\n## Configuration\n\nConfigure the indexer using environment variables or a `.env` file:\n\n```bash\n# Folders to monitor (comma-separated)\nWATCH_FOLDERS=\"/Users/me/Documents,/Users/me/Research\"\n\n# LanceDB storage path\nLANCEDB_PATH=\"./vector_index\"\n\n# Ollama model for summarization\nLLM_MODEL=\"llama3.2:3b\"\n\n# Text chunking settings\nCHUNK_SIZE=1000\nCHUNK_OVERLAP=200\n\n# Embedding model (sentence-transformers)\nEMBEDDING_MODEL=\"all-MiniLM-L6-v2\"\n\n# File types to index\nFILE_EXTENSIONS=\".pdf,.docx,.doc,.txt,.md,.rtf\"\n\n# Maximum file size in MB\nMAX_FILE_SIZE_MB=100\n\n# Ollama API URL\nOLLAMA_BASE_URL=\"http://localhost:11434\"\n```\n\n##…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_yairwein-mcp-doc-indexer","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.848,"provenance":"derived"}],"categories":["data","dev"],"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":"iflow-mcp_yairwein-mcp-doc-indexer","registry":"pypi","observedAt":"2026-09-15T20:21:40.261Z","publishedAt":"2026-02-13T18:47:39.199522Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_yairwein-mcp-doc-indexer","url":"https://pypi.org/project/iflow-mcp_yairwein-mcp-doc-indexer/","firstSeenAt":"2026-09-09T21:25:11.652Z","fetchedAt":"2026-09-15T20:20:55.034Z","normalizedAt":"2026-09-15T20:20:55.034Z"}]},"firstSeenAt":"2026-09-09T21:25:11.652Z","updatedAt":"2026-09-15T20:21:40.261Z"}