verdict-mcp

Dgotlieb/verdict-mcp

★ 0 stars Python Code/Dev Tools Updated 3d ago

Structured, sandboxed test feedback for coding agents — an MCP server returning tiny typed verdicts with failure fingerprints and history

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "verdict-mcp": {
      "command": "uvx",
      "args": [
        "verdict-mcp"
      ]
    }
  }
}

Or install with pip: pip install verdict-mcp

README Excerpt

https://github.com/user-attachments/assets/62923912-98aa-4246-8bc8-4adf55ae3ff8 **Structured, sandboxed verification feedback for coding agents.** An [MCP](https://modelcontextprotocol.io) server that replaces your agent's `pytest` shell-outs with something built for the agent inner loop: impact-selected tests, run in an isolated environment, returning **compact typed verdicts** instead of 40,000 tokens of raw runner output — with **failure fingerprints** that tell the agent whether a failure is

Tools (1)

preexisting

Topics

ai-agentsclaude-codemcpmodel-context-protocolpytesttesting

verdict-mcp

Quick Install

README Excerpt

Tools (1)

Topics

Related Code/Dev Tools Servers