{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9cz5z4q55aj6","handle":"mcp-server-rag","url":"https://wellknown.network/agents/mcp-server-rag","links":{"self":"https://wellknown.network/agents/mcp-server-rag/record.json","html":"https://wellknown.network/agents/mcp-server-rag","markdown":"https://wellknown.network/agents/mcp-server-rag/record.md","api":"https://wellknown.network/api/v1/agents/mcp-server-rag","status":"https://wellknown.network/api/v1/agents/mcp-server-rag/status","claim":"https://wellknown.network/agents/mcp-server-rag/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-server-rag/claim.json","badge":"https://wellknown.network/agents/mcp-server-rag/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-server-rag/history","tools":"https://wellknown.network/api/v1/agents/mcp-server-rag/tools"},"ard":{"identifier":"urn:air::server:mcp-server-rag","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-server-rag","summary":"MCP RAG server","description":"# MCP Server RAG\n\nRAG (Retrieval-Augmented Generation) server for MCP (Model Control Protocol). This server provides vector-based document retrieval functionality to enhance LLM interactions with contextual information.\n\n## Overview\n\nThe MCP Server RAG implementation provides a bridge between your LLM applications and document collections, offering:\n\n- Vector-based document search using ChromaDB and Sentence Transformers\n- Multiple specialized collections (liv, ken, ufa, sap commerce)\n- Strongly typed API responses\n- Integration with the MCP server infrastructure\n\n## Installation\n\n```bash\npip install rag-mcp-server\n```\n\n## Usage\n\nAfter installation, you can run the server with:\n\n```bash\nmcp-server-rag\n```\n\nOr using Python module syntax:\n\n```bash\npython -m mcp_server_rag\n```\n\n## Features\n\n- Vector-based search for contextual document retrieval\n- Persistent storage of document embeddings via ChromaDB\n- Multiple collection support for domain-specific searches\n- Configurable via environment variables\n- Fully typed response objects with detailed metadata\n- Seamless integration with the MCP protocol\n\n## Available Collections\n\nThe server provides access to four specialized collections:\n\n- `liv-rag`: LIV document collection (`retrieve_liv_context` tool)\n- `ken-rag`: Kennametal document collection (`retrieve_ken_context` tool)\n- `ufa-rag`: UFA document collection (`retrieve_ufa_context` tool)\n- `sap-comm-rag`: SAP Commerce document collection (`retrieve_sap_comm_context` tool)\n\n## Configuration\n\nThe following environment variables can be used to configure the server:\n\n| Variable | Description | Default |\n|----------|-------------|--------|\n| `RAG_PERSIST_DIR` | Directory where ChromaDB will store its data | `~/Documents/chroma_db` |\n| `RAG_EMBEDDING_MODEL` | Path or name of the Sentence Transformer model | `~/LLM/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/...` |\n| `RAG_N_RESULTS` | Default number of results to return from searches | `5` |\n\n## Dependenci…","publisher":null,"homepage":null,"repository":null,"version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-server-rag","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"}],"categories":["ai","data"],"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-server-rag","registry":"pypi","observedAt":"2026-11-03T16:25:49.324Z","publishedAt":"2025-04-19T10:20:39.397253Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-server-rag","url":"https://pypi.org/project/mcp-server-rag/","firstSeenAt":"2026-09-10T04:22:12.053Z","fetchedAt":"2026-11-03T16:23:20.581Z","normalizedAt":"2026-11-03T16:23:20.581Z"}]},"firstSeenAt":"2026-09-10T04:22:12.053Z","updatedAt":"2026-11-03T16:25:49.324Z"}