Safeagent

Overview

Safeagent is a Model Context Protocol server that acts as an exactly-once execution guard for AI agents. It prevents duplicate payments and webhooks from triggering on retry, ensuring safe and reliable agent operations without unwanted repetition.

The server runs locally on your machine through the Python package safeagent-exec-guard, installed via uvx. It communicates with MCP clients over stdio and requires no authentication to get started. Version v0.1.22 is available under the Apache-2.0 license, with source code hosted at azender1/SafeAgent on GitHub.

Safeagent belongs in the AI & Agents category on mcp.site and works with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim your listing to earn the Verified badge and ensure the information stays accurate.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}