{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mtpnc4abvxhb","handle":"hybrid-search-mcp","url":"https://wellknown.network/agents/hybrid-search-mcp","links":{"self":"https://wellknown.network/agents/hybrid-search-mcp/record.json","html":"https://wellknown.network/agents/hybrid-search-mcp","markdown":"https://wellknown.network/agents/hybrid-search-mcp/record.md","api":"https://wellknown.network/api/v1/agents/hybrid-search-mcp","status":"https://wellknown.network/api/v1/agents/hybrid-search-mcp/status","claim":"https://wellknown.network/agents/hybrid-search-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/hybrid-search-mcp/claim.json","badge":"https://wellknown.network/agents/hybrid-search-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/hybrid-search-mcp/history","tools":"https://wellknown.network/api/v1/agents/hybrid-search-mcp/tools"},"ard":{"identifier":"urn:air::server:hybrid-search-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"hybrid-search-mcp","summary":"MCP server for Hybrid Search - provides read-only access to collections and chunks via FastAPI backend","description":"# Hybrid Search MCP Server\n\nAn MCP (Model Context Protocol) server that provides read-only access to the Hybrid Search knowledge base. Enables AI assistants in Windsurf, VS Code, Open Code, and Claude Desktop to query collections and search documents using hybrid search (semantic + keyword with RRF ranking).\n\n> **⚠️ IMPORTANT PREREQUISITE**\n> \n> This MCP server requires the Hybrid Search container stack to be running in order to work. The MCP server does not directly access the database - it communicates with the Hybrid Search backend API.\n\nWhen you install the Hybrid Search container stack, it automatically ensures that the backend API is available at `http://localhost:8000`.\n\n## Features\n\n- **List Collections**: View all available knowledge base collections\n- **Get Collection Details**: See document counts, chunk counts, and metadata\n- **List Files**: View all files in a collection with chunk counts\n- **Hybrid Search**: Search using semantic AI + keyword matching with Reciprocal Rank Fusion\n\n## Prerequisites\n\n- Python 3.11+\n- [uv](https://docs.astral.sh/uv/) package manager (recommended)\n- Hybrid Search backend running at `http://localhost:8000`\n\n## Installation\n\n### From PyPI (Recommended)\n\nOnce published to PyPI, you can install with:\n\n```bash\n# Using pip\npip install hybrid-search-mcp\n\n# Using uvx (run without installing)\nuvx hybrid-search-mcp\n\n# Using pipx (isolated environment)\npipx install hybrid-search-mcp\n```\n\n### From Source\n\n#### Using uv (Recommended)\n\n```bash\ncd mcp-server\nuv sync\n```\n\n#### Using pip\n\n```bash\ncd mcp-server\npip install -e .\n```\n\n## Configuration\n\nThe MCP server connects to the Hybrid Search FastAPI backend. Configure via environment variables:\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `HYBRID_SEARCH_API_URL` | `http://localhost:8000` | Backend API base URL |\n| `HYBRID_SEARCH_API_TIMEOUT` | `30.0` | Request timeout in seconds |\n\n## Running the Server\n\n### If Installed via pip/uvx\n\n```bash\n# Direct comma…","publisher":{"name":"Krishna Bandi","url":null},"homepage":"https://github.com/krishna1306/mcp-server-hybrid-search/blob/main/README.md","repository":"https://github.com/krishna1306/mcp-server-hybrid-search/blob/main/README.md","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["hybrid-search","knowledge-base","mcp","model-context-protocol","rag","semantic-search"],"pricing":null,"endpoints":[{"url":"pypi:hybrid-search-mcp","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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"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":"hybrid-search-mcp","registry":"pypi","observedAt":"2026-09-15T16:22:22.006Z","publishedAt":"2026-05-28T04:09:56.403894Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"hybrid-search-mcp","url":"https://pypi.org/project/hybrid-search-mcp/","firstSeenAt":"2026-09-09T17:21:42.306Z","fetchedAt":"2026-09-15T16:21:19.282Z","normalizedAt":"2026-09-15T16:21:19.282Z"}]},"firstSeenAt":"2026-09-09T17:21:42.306Z","updatedAt":"2026-09-15T16:22:22.006Z"}