{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pbd25v3xg4fz","handle":"rag-mcp-2","url":"https://wellknown.network/agents/rag-mcp-2","links":{"self":"https://wellknown.network/agents/rag-mcp-2/record.json","html":"https://wellknown.network/agents/rag-mcp-2","markdown":"https://wellknown.network/agents/rag-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/rag-mcp-2","status":"https://wellknown.network/api/v1/agents/rag-mcp-2/status","claim":"https://wellknown.network/agents/rag-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/rag-mcp-2/claim.json","badge":"https://wellknown.network/agents/rag-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:rag-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"rag-mcp","summary":"This is a local rag-mcp solution with chromadb using langchain and docling","description":"# RAG MCP: Document Processing Server\n\nA Retrieval-Augmented Generation (RAG) server built on the Model Context Protocol (MCP) for intelligent document processing and question answering.\n\n## Overview\n\nRAG MCP is a tool that allows you to index various document formats and perform semantic searches against them. It uses advanced embedding techniques and vector databases to make your documents searchable through natural language queries.\n\n## Features\n\n- **Document Indexing**: Support for various document formats (PDF, DOCX, XLSX, PPTX, Markdown, AsciiDoc, HTML, XHTML, CSV)\n- **Semantic Search**: Query your documents using natural language\n- **Flexible Embedding Models**: Choose between HuggingFace BGE (default) or Ollama embeddings.\n- **High Performance**: Optimized for various hardware configurations with automatic device selection (CUDA, MPS, CPU) for HuggingFace embeddings.\n- **Persistent Storage**: Vector embeddings are stored locally for future use\n\n## Requirements\n\n- Python 3.11+\n- Environment with access to your documents\n- (Optional) Ollama installed and running if using Ollama embeddings.\n\n## Installation\n\n### 1. Install UV\n\nFirst, you need to install UV, a Python package installer and resolver:\n\n#### On macOS/Linux:\n```bash\ncurl -sSf https://astral.sh/uv/install.sh | sh\n```\n\n#### On Windows:\n```bash\npowershell -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\n### 2. Run RAG MCP\n\nOnce UV is installed, you can run RAG MCP directly using:\n\n```bash\nuvx rag-mcp\n```\n\nThis will start the MCP server and make it available for document processing.\n\n**Environment Variables:**\n\nYou can configure RAG MCP using environment variables:\n\n-   `PERSIST_DIRECTORY` (Required): Path to the directory where the vector database will be stored (e.g., `/path/to/your/persist/directory`). A `chromadb` subfolder will be created here.\n-   `USE_OLLAMA_EMBEDDING` (Optional): Set to `True` to use Ollama embeddings instead of the default HuggingFace BGE embeddings. Requires Ollama to be r…","publisher":null,"homepage":null,"repository":null,"version":"0.1.4","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:rag-mcp","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":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"ai.model-access","name":"Model Access","confidence":0.905,"provenance":"derived"},{"slug":"infra.devices","name":"Devices & IoT","confidence":0.802,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.722,"provenance":"derived"}],"categories":["ai","data","documents","infra"],"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":"rag-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:08.550Z","publishedAt":"2025-04-15T17:21:02.684154Z","latestVersion":"0.1.4"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"rag-mcp","url":"https://pypi.org/project/rag-mcp/","firstSeenAt":"2026-09-10T11:25:57.378Z","fetchedAt":"2026-09-10T11:25:57.378Z","normalizedAt":"2026-09-10T11:25:57.378Z"}]},"firstSeenAt":"2026-09-10T11:25:57.378Z","updatedAt":"2026-09-10T11:28:08.550Z"}