it-beard_exa-server

MCP.Pizza Chef: MCP-Mirror

The it-beard_exa-server is an MCP server that enables AI-driven code search capabilities by leveraging the Exa API. It allows users to perform natural language queries to find relevant code examples and documentation efficiently. The server returns results in a structured JSON format enriched with metadata, making it ideal for integration into developer tools and AI workflows. It supports configuration of the number of search results and is designed to be easily installed and configured with an Exa API key. This server enhances developer productivity by providing quick, context-aware code search powered by AI.

Use This MCP server To

Perform natural language code searches within development environments Retrieve relevant code examples and documentation programmatically Integrate AI-powered code search into IDEs or code editors Automate code snippet discovery for faster development Provide structured JSON responses for downstream AI processing

README

Exa MCP Server

An MCP (Model Context Protocol) server that provides AI-powered code search capabilities using the Exa API.

Features

  • Perform AI-powered code searches using natural language queries
  • Get relevant code examples and documentation
  • Configurable number of search results
  • JSON response format with rich metadata

Installation

  1. Clone this repository:
git clone https://github.com/it-beard/exo-server.git
cd exa-server
  1. Install dependencies:
npm install
  1. Build the project:
npm run build
  1. Configure your Exa API key in the MCP settings file (tested with Cline):
{
  "mcpServers": {
    "exa": {
      "command": "node",
      "args": ["/path/to/exa-server/build/index.js"],
      "env": {
        "EXA_API_KEY": "your-api-key-here"
      }
    }
  }
}

Usage

The server provides the following tools and resources:

Tools

search

Perform an AI-powered search using Exa API

Input Schema:

{
  "query": "Search query",
  "numResults": 10
}

Resources

  • exa://search/{query} - Search results for a specific query
  • exa://last-search/result - Results from the most recent search query

Development

  1. Make your changes in the src directory
  2. Build the project:
npm run build
  1. Test your changes by configuring the server in your MCP settings

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

it-beard_exa-server FAQ

How do I install the it-beard_exa-server?
Clone the repository, install dependencies with npm, build the project, and configure your Exa API key in the MCP settings file.
How do I configure the Exa API key for the server?
Set the EXA_API_KEY environment variable in the MCP server configuration to your valid Exa API key.
What format does the server return search results in?
The server returns search results in JSON format with rich metadata for easy parsing and integration.
Can I control the number of search results returned?
Yes, the server supports configuration of the number of search results to tailor responses to your needs.
Is the it-beard_exa-server compatible with multiple LLM providers?
While the server itself focuses on code search via Exa API, it can be integrated with MCP clients using models from OpenAI, Claude, Gemini, and others.
What kind of queries can I perform with this server?
You can perform natural language queries to search for code snippets, examples, and related documentation.
How do I run the it-beard_exa-server after installation?
Use the configured MCP command to start the server, typically running 'node /path/to/exa-server/build/index.js' with the appropriate environment variables set.
Does the server provide any tools or APIs?
Yes, it exposes a 'search' tool that accepts natural language queries and returns AI-powered code search results.