evalview-mcp

local MCP server

Installation

Terminal

claude mcp add evalview-mcp -e OPENAI_API_KEY=... -- uvx evalview

Run in your project folder. Add --scope user to use it everywhere.

Claude Desktop, Cursor & other clients

Add to claude_desktop_config.json or .cursor/mcp.json.

{
  "mcpServers": {
    "evalview-mcp": {
      "command": "uvx",
      "args": [
        "evalview"
      ],
      "env": {
        "OPENAI_API_KEY": "..."
      }
    }
  }
}

Fill in the environment variables with your own credentials.

Summary

Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

Questions

evalview-mcp is a local MCP server distributed as the pypi package evalview.

Run: claude mcp add evalview-mcp -e OPENAI_API_KEY=... -- uvx evalview

Run: codex mcp add evalview-mcp --env OPENAI_API_KEY=... -- uvx evalview

Similar MCP servers

NameStars

claude-code-organizerio.github.mcpware/claude-code-organizer381
HeyClaude — Claude & AI workflow directoryio.github.JSONbored/heyclaude300
lmio.github.houtini-ai/lm119
Zikkaronio.github.amanhij/zikkaron63
heraldio.github.btouchard/herald46
genexusio.github.lennix1337/genexus35
janeeio.github.rsdouglas/janee30
batontech.kasabeh/baton27