mcpmark
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
- 467 stars
- 50 forks
- 24 open issues
- Language: Python
- License: Apache-2.0
- updated
Install
local · uvx (python)claude mcp add mcpmark -- uvx mcpmark{
"mcpServers": {
"mcpmark": {
"command": "uvx",
"args": ["mcpmark"]
}
}
}{
"mcpServers": {
"mcpmark": {
"command": "uvx",
"args": ["mcpmark"]
}
}
}- Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
- Replace any <placeholder> values with your API keys or paths.
- Restart Claude. The MCP server and its tools appear automatically.
Package name inferred from the repository name. Verify it exists on PyPI, or clone https://github.com/eval-sys/mcpmark and follow its README.
MCP Servers overview
What people ask about mcpmark
What is eval-sys/mcpmark?
eval-sys/mcpmark is mcp servers for the Claude AI ecosystem. MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use. It has 467 GitHub stars and its last recorded update is dated 2026-06-12.
How do I install mcpmark?
You can install mcpmark by cloning the repository (https://github.com/eval-sys/mcpmark) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is eval-sys/mcpmark safe to use?
Our security agent has analyzed eval-sys/mcpmark and assigned a Trust Score of 92/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains eval-sys/mcpmark?
eval-sys/mcpmark is maintained by eval-sys. The last recorded GitHub activity is dated 2026-06-12, with 24 open issues.
Are there alternatives to mcpmark?
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.