
Executor
Executor gives an agent one MCP endpoint for the services you connect once, such as OpenAPI specs, remote MCP servers, GraphQL APIs and custom TypeScript apps, and it attaches your API keys or OAuth sign-ins so the agent never sees a credential. The agent gets two tools, skills and execute: it searches for what it needs and runs a short program across your apps, and each tool can ask for your approval before it runs.
- GitHub stars
- 4.5K
- auth
- Required
- transport
- HTTP
- last updated
- Nov 15, 2026
Sponsors
Readme
Executor
Everything your agent needs, drivable as code.
Think of Executor as Zapier or Retool, but fully drivable as code, with everything exposed to your agent. Connect the services you already use once, and any agent can use them through one MCP endpoint, without ever seeing a credential.
Website · Documentation · Discord · Launch post
https://github.com/user-attachments/assets/126c8117-2ef7-4f96-8fb8-8871728b0102
What it does
You have an agent, and you want it to call something: an API, an MCP server, a CLI, a service with no spec at all. Usually that means pasting the same keys into every client, wiring the same servers up again, and writing an exception for every API that does not fit the format.
Executor gives all of that one shape: the app. An app is a small TypeScript program that turns your accounts into tools. One app can wrap an OpenAPI spec, proxy a remote MCP server, or call an API by hand. It can also store data, serve its own UI, run in the background, and ask before it does anything risky.
Details
- Repository
- github.com/UsefulSoftwareCo/executor
- Website
- executor.sh
- Categories
- AI & LLM Tools, Automation & Workflows
- Transport
- HTTP
- Auth
- Required