Mcpmark

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

開源上線中

0 0

安裝

git clone https://github.com/eval-sys/mcpmark.git

pip install -e .

取自專案的 README。執行前請先確認它會做什麼。

README 掃描安全

README 要你執行的指令中，沒有發現有風險的內容。

需要 API 金鑰或 tokenOPENAI_API_KEY="sk-..."

我們只掃描 README，不掃描程式碼。沒有發現問題不代表一定安全。掃描方式

Mcpmark 的替代方案

同類型中主題重疊最多的項目，星數多的排前面。

HolaOS

Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Clau

11k

Cursor Talk To Figma Mcp

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

7.1k

Openagent

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

5.7k

ADR

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

2.1k

Aseprite Ai Artist

Your coding agent paints pixel art in the Aseprite window you already have open. MCP server + skills for Claude Code, omp, Codex, Gemini CLI and Cursor — draws, looks at its work, animates and exports

694

Tunnel Client

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

637

在 GitHub 查看

程式碼庫

星數: 473
Fork 數: 50
最近更新: 2026年6月12日
授權條款: Apache-2.0
語言: Python
建立日期: 2025年7月1日
未結 issue: 27
品質分數: B 58/100

eval-sys/mcpmark

每天從 GitHub 讀取。

查看替代方案

價格

開源

Maker

尚未有人認領。

登入後即可認領這個工具。

Mcpmark

安裝

README 掃描安全

標籤

Mcpmark 的替代方案

程式碼庫

價格

Maker