UsefulSoftwareCo/executor

The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.

What it solves

Executor provides a centralized integration layer for AI agents. Instead of configuring API keys, MCP servers, and tool policies for every individual agent (like Claude Code or Cursor), you configure them once in Executor and share that single catalog of tools across all your MCP-compatible agents.

How it works

Executor acts as a middleware between agents and external tools. It allows you to:

  1. Add Integrations: Connect to MCP servers, OpenAPI specifications, GraphQL APIs, or Google Discovery.
  2. Create Connections: Set up authenticated instances of those integrations.
  3. Set Policies: Define whether specific tools are always allowed, require manual approval, or are blocked entirely.
  4. Connect Agents: Point your agents to Executor via the Model Context Protocol (MCP), allowing them to access the shared tool catalog.

Who it’s for

Developers and AI agent users who use multiple different AI clients and want a single, governed source of truth for their tool integrations and credentials.

Highlights

  • Broad Integration Support: First-party support for OpenAPI, GraphQL, and MCP servers.
  • Flexible Deployment: Can be run as a hosted cloud service, a local CLI, a desktop app, or self-hosted via Docker and Cloudflare Workers.
  • Policy-Based Governance: Centralized control over which tools agents can execute and whether they need approval.
  • MCP Compatible: Works with any agent that supports the Model Context Protocol.

Related

  • Project
    different-ai/openwork

    An open-source desktop app and MCP server that allows users to share and reuse AI workflows, skills, and connected services across multiple AI agents and teammates.

  • Project
    mondaycom/mcp

    An open framework and MCP server that enables AI agents to securely interact with monday.com to manage projects, track tasks, and execute workflows.

  • Project
    apify/mcpc

    A universal CLI client for the Model Context Protocol (MCP) that enables AI agents and developers to interact with MCP servers via shell commands.

  • Project
    milisp/mcp-linker

    A cross-platform manager that allows users to one-click install and sync MCP servers across multiple AI clients from a built-in marketplace.

  • Project
    docker/mcp-gateway

    A Docker CLI plugin that provides a gateway for managing and deploying isolated, containerized MCP servers for AI clients.