{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_myacxedddw8f","handle":"rag-retrieval-mcp","url":"https://wellknown.network/agents/rag-retrieval-mcp","links":{"self":"https://wellknown.network/agents/rag-retrieval-mcp/record.json","html":"https://wellknown.network/agents/rag-retrieval-mcp","markdown":"https://wellknown.network/agents/rag-retrieval-mcp/record.md","api":"https://wellknown.network/api/v1/agents/rag-retrieval-mcp","status":"https://wellknown.network/api/v1/agents/rag-retrieval-mcp/status","claim":"https://wellknown.network/agents/rag-retrieval-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/rag-retrieval-mcp/claim.json","badge":"https://wellknown.network/agents/rag-retrieval-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:rag-retrieval-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"rag-retrieval-mcp","summary":"A generic RAG MCP server with pluggable embedding providers and vector stores","description":"# MCP Server for RAG Retrieval\n\nA generic Retrieval-Augmented Generation (RAG) Model Context Protocol (MCP) server with pluggable embedding providers and vector stores.\n\n## Why this server?\n\nVendor MCP servers usually only support their (own) integrated embedding models. If your index uses external embeddings (e.g., OpenAI), those servers can't query it. This server fills that gap — it embeds your query with the provider of your choice, then searches any supported vector store.\n\n## Currently Supports\n\n**Embedding Providers:**\n- OpenAI (`text-embedding-3-small`, `text-embedding-3-large`, `text-embedding-ada-002`, etc.)\n\n**Vector Stores:**\n- Pinecone\n- pgvector (PostgreSQL)\n\n## Tools\n\n### `retrieve`\n\nSearch a knowledge base and return relevant content.\n\n**Parameters:**\n- `query` (string, required) — The search query to find relevant content.\n\n**Returns** a JSON array of results, each with `text`, `score`, and `metadata` fields.\n\n## Install & Run\n\nRun directly with `uvx` (no install needed):\n\n```bash\nuvx rag-retrieval-mcp[all]\n```\n\nOr install with pip:\n\n```bash\npip install rag-retrieval-mcp[all]\nrag-retrieval-mcp\n```\n\n### MCP client configuration\n\n```json\n{\n  \"mcpServers\": {\n    \"rag-retrieval\": {\n      \"command\": \"uvx\",\n      \"args\": [\"rag-retrieval-mcp[all]\"],\n      \"env\": {\n        \"OPENAI_API_KEY\": \"your-openai-api-key\",\n        \"PINECONE_API_KEY\": \"your-pinecone-api-key\",\n        \"PINECONE_HOST\": \"your-pinecone-index-host-url\"\n      }\n    }\n  }\n}\n```\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|---|---|---|---|\n| `RAG_EMBEDDING_PROVIDER` | No | `openai` | Embedding provider to use |\n| `RAG_VECTOR_STORE` | No | `pinecone` | Vector store to use |\n| `RAG_TOP_K` | No | `5` | Number of results to return |\n| `OPENAI_API_KEY` | Yes (if using OpenAI) | | OpenAI API key |\n| `OPENAI_EMBEDDING_MODEL` | No | `text-embedding-3-small` | OpenAI embedding model |\n| `PINECONE_API_KEY` | Yes (if using Pinecone) | | Pinecone API key |\n| `PINECONE_HOST…","publisher":{"name":"MaryamZi","url":null},"homepage":null,"repository":"https://github.com/MaryamZi/rag-retrieval-mcp","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp","rag","retrieval","embeddings","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:rag-retrieval-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.814,"provenance":"derived"}],"categories":["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":"rag-retrieval-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:08.888Z","publishedAt":"2026-03-25T06:37:30.662452Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"rag-retrieval-mcp","url":"https://pypi.org/project/rag-retrieval-mcp/","firstSeenAt":"2026-09-10T11:25:58.367Z","fetchedAt":"2026-09-10T11:25:58.367Z","normalizedAt":"2026-09-10T11:25:58.367Z"}]},"firstSeenAt":"2026-09-10T11:25:58.367Z","updatedAt":"2026-09-10T11:28:08.888Z"}