mcp-agent

Overview

MCP Agent is a development framework that enables seamless integration of MCP tools with LLM clients. Written in Rust, it provides a structured approach for developers to build MCP tools by leveraging large language model capabilities. The framework manages the integration of dependent MCP tools and LLM clients, allowing developers to focus on implementing their specific business logic. It features a flexible configuration system using TOML files, support for multiple MCP servers, and configurable LLM parameters.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

Comparable tools

Installation

# From crates.io
mcp-agent = "0.1.0"

# Or from GitHub
mcp-agent = { git = "https://github.com/CeerDecy/mcp-agent", branch = "main" }

cargo build

{
  "mcpServers": {
    "mcp-agent": {
      "command": "path/to/your/executable",
      "args": []
    }
  }
}

FAQ

What MCP servers are supported by this framework?

The framework supports any MCP servers that can be configured with command and arguments. It includes examples for searxng and fetch servers, but it's designed to work with any MCP-compliant server.

Can I use different LLM providers with MCP Agent?

Yes, the framework supports configurable LLM parameters including API key, base URL, and model name, making it compatible with various LLM providers that implement the async-openai client interface.

Compare mcp-agent with