
mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
What is mcp-local-rag?
The mcp-local-rag is a "primitive" RAG-like web search model context protocol (MCP) server that operates locally without the need for APIs.
How to use mcp-local-rag?
To use mcp-local-rag, you need to install the uv
package and configure it in your Claude settings. You can either clone the repository or use a direct configuration method to set it up.
Key features of mcp-local-rag?
- Local operation without API dependencies
- Integration with Claude for enhanced web search capabilities
- Simple installation and configuration process
Use cases of mcp-local-rag?
- Enhancing AI models with up-to-date web search results.
- Running local web searches for specific queries.
- Integrating with other AI systems for improved context awareness.
FAQ from mcp-local-rag?
- Is mcp-local-rag free to use?
Yes! mcp-local-rag is free to use for everyone.
- What programming language is mcp-local-rag written in?
mcp-local-rag is written in Python.
- Can I run mcp-local-rag on any operating system?
Yes, as long as you have Python and the required dependencies installed.

mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨

Installation instructions
- You would need to install
uv
: https://docs.astral.sh/uv/
If you do not want to clone in Step 2.
Just paste this directly into Claude config. You can find the configuration paths here: https://modelcontextprotocol.io/quickstart/user
{
"mcpServers": {
"mcp-local-rag":{
"command": "uvx",
"args": [
"--python=3.10",
"--from",
"git+https://github.com/nkapila6/mcp-local-rag",
"mcp-local-rag"
]
}
}
}
Otherwise:
- Clone this GitHub repository (OPTIONAL, can be skipped with above config)
git clone https://github.com/nkapila6/mcp-local-rag
- Add the following to your Claude config. You can find the configuration paths here: https://modelcontextprotocol.io/quickstart/user
{
"mcpServers": {
"mcp-local-rag": {
"command": "uv",
"args": [
"--directory",
"<path where this folder is located>/mcp-local-rag/",
"run",
"src/mcp_local_rag/main.py"
]
}
}
}
Example use
On prompt
When asked to fetch/lookup/search the web, the model prompts you to use MCP server for the chat.
In the example, have asked it about Google's latest Gemma models released yesterday. This is new info that Claude is not aware about.
Result
The result from the local rag_search
helps the model answer with new info.
