LocalFree

Agent Eval MCP server

RudrenduPaul/agent-eval

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

0 GitHub stars
Source code

Install Agent Eval in Claude Code

Claude Code
claude mcp add agent-eval -- uvx agent-regress-cli
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "agent-eval": {
      "command": "uvx",
      "args": [
        "agent-regress-cli"
      ]
    }
  }
}

Frequently asked questions

What does the Agent Eval MCP server do?

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

Is the Agent Eval MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Agent Eval run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Agent Eval to Claude Code?

Run: claude mcp add agent-eval -- uvx agent-regress-cli

More ai agents & coding agents MCP servers

View all

Agent Guard

0

liminalpepe/agent-guard-mcp

Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.

LocalFree

Agent Cost

0

vk0dev/agent-cost-mcp

Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.

LocalFree

Agent Guardrail

0

eren-solutions/agent-guardrail

Action-level governance for AI agents -- control what they DO, not what they SAY

LocalFree

Agent Config Bridge

0

onehumanbeing/agent-config-bridge

Convert CLAUDE.md, AGENTS.md, Cursor rules, GEMINI.md and MCP configs between coding agents.

LocalFree

Agent Harness

01.7k

cuonztech/agent-harness

MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.

LocalFree

Agent Claim

0

vk0dev/agent-claim-mcp

File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.

LocalFree