GitHub 仓库

eval-sys/mcpmark

Python 首次收录 2025-07-01 更新于 2026-07-16 查看源 ↗

GitHub 仓库 中按Star排名第 733 / 共 783

443 Star

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

项目介绍

An evaluation suite for agentic models in real MCP tool environments (Notion / GitHub / Filesystem / Postgres / Playwright).

MCPMark provides a reproducible, extensible benchmark for researchers and engineers: one-command tasks, isolated sandboxes, auto-resume for failures, unified metrics, and aggregated reports.

🚀 MCPMark Verified is now the default. The standard tasks in this repository are the Verified set — every environment version-pinned and every verifier stabilized. Results from earlier task versions are deprecated and not directly comparable, so please report new numbers as MCPMark Verified. On the Verified set, gpt-5.5 (xhigh) leads at 92.9% and kimi-k2.7 reaches 81.1%. See…

摘自 github.com/eval-sys/mcpmark

最新指标

Star 443 2026-07-16
Fork 40 2026-07-16
提交 448 2026-07-16
发布 4 2026-07-16
Watcher 7 2026-07-16
开放 issue 14 2026-07-16
开放 PR 4 2026-07-16