@ragrabbit/mcp
About
Open Source, Self-Hosted, AI Search and LLM.txt for your website
Details
- Author
- madarco
- GitHub stars
- 135
- Downloads
- 248
- Categories
- Other
Jump to
- Semantic search across documentation with natural language queries
- Standardized communication via the Model Context Protocol
- Custom naming for the documentation service
- Exposes a search_docs tool with a query parameter
- Provides an llms.txt resource with LLM-specific documentation
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
@ragrabbit/mcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install it as an MCP server in Claude Desktop or Cursor IDE by running npx @ragrabbit/mcp with two required arguments: the base URL of your RagRabbit instance and a custom name for the documentation service. In Claude Desktop, add a server entry in claude_desktop_config.json; in Cursor, add a command-type MCP in Settings → MCP.
search_docs
Retrieve relevant documents about <name of your documentation> based on a query
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"@ragrabbit/mcp": {
"<name_of_your_documentation_no_spaces>": {
"command": "npx",
"args": [
"@ragrabbit/mcp",
"http://<RagRabbit install>/",
"<name of your documentation>"
]
}
}
}
}McpServers
{
"<name_of_your_documentation_no_spaces>": {
"command": "npx",
"args": [
"@ragrabbit/mcp",
"http://<RagRabbit install>/",
"<name of your documentation>"
]
}
}MCP Server for RagRabbit Documentation Search
This server implements the Model Context Protocol (MCP) to provide AI models with access to any documentation indexed with an instance of RagRabbit.
Overview
The MCP Server acts as a bridge between AI clients and RagRabbit's hosted documentation:
- Semantic search across documentation using natural language queries
- Access to LLM-specific documentation
- Standardized communication through the Model Context Protocol
Installation
Claude Desktop
Add a custom mcp server with the name of your product, so that Claude AI can use it when looking for info about it.
in claude_desktop_config.json (Claude -> Settings -> Developer -> Edit Config)
{
"mcpServers": {
"<name_of_your_documentation_no_spaces>": {
"command": "npx",
"args": ["@ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"]
}
}
}
In Cursor IDE
Go to Cursor -> Settings -> Cursor Settings -> MCP
And add a new MCP of type command with the command:
npx @ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"
Arguments:
- ragrabbit-url: (Required) The base URL of your RagRabbit instance, eg https://my-ragrabbit.vercel.com/
- name: (Required) Custom name for the documentation search service (defaults to "RagRabbit") so that AI will know to use it when looking for info
Exposed Tools by this MCP
search_docs
Performs semantic search across the documentation.
Parameters:
- query: String - The search query to find relevant documents
Example:
{
"name": "search_docs",
"arguments": {
"query": "How to implement authentication?"
}
}
Available Resources
LLMs Documentation
- URI: llms.txt
- Description: Documentation about LLMs and their capabilities
- MIME Type: text/plain
License
MIT
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
