Evr

Overview

Evr is a Model Context Protocol (MCP) server: Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true. In practice that means any MCP-compatible AI assistant can call Evr's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package evidence-readiness (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.1.2, published under the Apache-2.0 license, with source at evidence-readiness/spec on GitHub.

Evr is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Evr for evidence-readiness, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "evr": {
      "command": "uvx",
      "args": [
        "evidence-readiness"
      ]
    }
  }
}