shinpr/mcp-local-rag
by Various
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
MCP
shinpr/mcp-local-rag
Added 1 June 2026
Overview
Local-first RAG server for developers. Performs semantic and keyword search over code and technical documents. Runs as an MCP server or CLI tool with zero setup and full data privacy.
Best for
Best for
Developers who need private, local search over code and docs without external dependencies.
Use cases
- Search codebases locally without sending data to the cloud
- Query technical documentation using natural language
- Integrate RAG capabilities into MCP-compatible development tools
How to use
Install
npx mcp-local-rag ingest ./docs/ Tools exposed
RAG_HYBRID_WEIGHTRAG_GROUPINGRAG_MAX_DISTANCERAG_MAX_FILESBASE_DIRBASE_DIRSDB_PATHCACHE_DIRMODEL_NAMEMAX_FILE_SIZECHUNK_MIN_LENGTHRAG_DEVICERAG_DTYPE
Tested with
Claude Code, Cursor
Example client config
{\n "mcpServers": {\n "local-rag": {\n "command": "npx",\n "args": ["-y", "mcp-local-rag"],\n "env": {\n "BASE_DIR": "/path/to/your/documents"\n }\n }\n }\n} Notes
Local-first RAG server for developers. Performs semantic and keyword search over code and technical documents. Runs as an MCP server or CLI tool with zero setup and full data privacy.
290 stars on GitHub. Last updated 2026-05-23. Licensed MIT.
Use cases
- Search codebases locally without sending data to the cloud
- Query technical documentation using natural language
- Integrate RAG capabilities into MCP-compatible development tools
Pros
- Fully private, no data leaves the machine
- Zero setup, works out of the box
- Supports both MCP and CLI interfaces
Cons
- Limited to local resources, may not handle very large datasets efficiently
- Small community with 290 stars, fewer integrations and extensions
- Relies on local compute, can be slower than cloud alternatives for complex queries
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Fully private, no data leaves the machine
- Zero setup, works out of the box
- Supports both MCP and CLI interfaces
Cons
- Limited to local resources, may not handle very large datasets efficiently
- Small community with 290 stars, fewer integrations and extensions
- Relies on local compute, can be slower than cloud alternatives for complex queries
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Milvus
Community
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Chroma
Community
Search infrastructure for AI
Qdrant
Community
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Open WebUI
Various
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
Community
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
Private GPT
Community
Interact with your documents using the power of GPT, 100% privately, no data leaks
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.