eval-sys / mcpmark
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
Why this job: name: mcp; topics: mcp-servers, mcp
What it does
An evaluation suite for agentic models in real MCP tool environments (Notion / GitHub / Filesystem / Postgres / Playwright).
Get started
pip install -e .
# If you'll use browser-based tasks, install Playwright browsers first
playwright install- Maintenance
- Active
- Last commit 5 months ago
- Stars
- 472
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.2.0
- Released 13 months ago
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 39% closed
- 22 still open
- Pull requests
- 209 merged
- 5 waiting
- Releases
- 4
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| serpapi / serpapi-mcp | 184 | 5 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 97%
- PLpgSQL 2%
- Shell 1%
- Dockerfile <1%
Topics
- agentic
- benchmark
- eval-sys
- mcp
- mcp-servers
- mcpmark
- tool-use
Project record
- JobMCP servers
- StatusListed
- Commits448
- Forks50
- Watching7
- Stars in 28 days+6
- CreatedJul 1, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026