{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_txfmfrxvshhz","handle":"claude-lfr-mcp","url":"https://wellknown.network/agents/claude-lfr-mcp","links":{"self":"https://wellknown.network/agents/claude-lfr-mcp/record.json","html":"https://wellknown.network/agents/claude-lfr-mcp","markdown":"https://wellknown.network/agents/claude-lfr-mcp/record.md","api":"https://wellknown.network/api/v1/agents/claude-lfr-mcp","status":"https://wellknown.network/api/v1/agents/claude-lfr-mcp/status","claim":"https://wellknown.network/agents/claude-lfr-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/claude-lfr-mcp/claim.json","badge":"https://wellknown.network/agents/claude-lfr-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/claude-lfr-mcp/history","tools":"https://wellknown.network/api/v1/agents/claude-lfr-mcp/tools"},"ard":{"identifier":"urn:air::server:claude-lfr-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"claude-lfr-mcp","summary":"Fast CPU-based RAG for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.","description":"# Claude LFR MCP\n\nLightning fast CPU-based semantic code search for Claude Code. Uses configurable embedding models and Qdrant vector database to provide intelligent code retrieval without requiring GPU resources.\n\n## Quick Start\n\n### Prerequisites\n\nA running Qdrant instance is required. Start one with Docker:\n\n```bash\ndocker run -p 6333:6333 qdrant/qdrant\n```\n\n### Installation\n\n```bash\nuv tool install claude-lfr-mcp\n```\n\n### Claude Code Setup\n\nAdd the MCP server to Claude Code project:\n\n```bash\nclaude mcp add claude-lfr -- claude-lfr-mcp\n```\n\nVerify the installation:\n\n```\n/mcp\n```\n\nYou should see `claude-lfr` listed with its available tools.\n\nThen ask claude to `index codebase`.\n\n## Embedding Models\n\nThis tool supports multiple embedding models, allowing you to choose the best tradeoff between speed, memory usage, and retrieval quality for your use case.\n\n### Model Comparison\n\n| Model | Dimension | Size | Speed | Quality | Best For |\n|-------|-----------|------|-------|---------|----------|\n| `all-MiniLM-L6-v2` | 384 | ~90MB | Fastest | Good | Quick prototyping, CI pipelines, large codebases |\n| `bge-small-en-v1.5` | 384 | ~67MB | Fast | Good+ | Balance of speed and accuracy |\n| `snowflake-arctic-embed-xs` | 384 | ~90MB | Fast | Good+ | Modern alternative to MiniLM |\n| `snowflake-arctic-embed-s` | 384 | ~130MB | Medium | Better | Production use with speed needs |\n| `bge-base-en-v1.5` | 768 | ~438MB | Slower | Best | **Default** - Best retrieval quality |\n| `nomic-embed-text-v1.5` | 768 | ~130MB | Medium | Better | When using Nomic ecosystem |\n\n### Model Details\n\n**all-MiniLM-L6-v2**\n- ✅ Fastest inference, smallest memory footprint\n- ✅ No query prefix required (simpler usage)\n- ❌ Lower retrieval accuracy than larger models\n- Best for: CI/CD pipelines, quick iteration, very large codebases where speed matters\n\n**bge-small-en-v1.5**\n- ✅ Excellent speed with better accuracy than MiniLM\n- ✅ Smallest download size (~67MB)\n- ❌ Requires \"query: \" prefix (handled automatic…","publisher":null,"homepage":null,"repository":"https://gitlab.com/derico/claude-lfr-mcp/-/issues","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["rag","code-search","embeddings","qdrant","mcp","claude-code","semantic-search","bge","vector-database","cpu-inference"],"pricing":null,"endpoints":[{"url":"pypi:claude-lfr-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"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":1,"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":"claude-lfr-mcp","registry":"pypi","observedAt":"2026-11-09T01:27:40.702Z","publishedAt":"2026-01-25T20:21:00.504555Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"claude-lfr-mcp","url":"https://pypi.org/project/claude-lfr-mcp/","firstSeenAt":"2026-09-09T11:30:50.434Z","fetchedAt":"2026-11-09T01:26:59.129Z","normalizedAt":"2026-11-09T01:26:59.129Z"}]},"firstSeenAt":"2026-09-09T11:30:50.434Z","updatedAt":"2026-11-09T01:27:40.702Z"}