MCPBench

by modelscope · Python · ★ 244

The evaluation benchmark on MCP servers

#benchmark#database#mcp#mcp-server#websearch

Install

pip install git+https://github.com/modelscope/MCPBench.git

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "mcpbench": {
      "command": "uvx",
      "args": [
        "git+https://github.com/modelscope/MCPBench.git"
      ]
    }
  }
}

From the README

🦊 MCPBench: A Benchmark for Evaluating MCP Servers [![Documentation][docs-image]][docs-url] [![Package License][package-license-image]][package-license-url] [中文](https://github.com/modelscope/MCPBench/blob/main/README_zh.md) | [English](https://github.com/modelscope/MCPBench/blob/main/README.md) MCPBench is an evaluation framework for MCP Servers. It supports the evaluation of three types of servers: Web Search, Database Query and GAIA, and is compatible with both local and remote MCP Servers. The framework primarily evaluates different MCP Servers (such as Brave Search, DuckDuckGo, etc.)…

Read full README on GitHub →