Executor
Unified tool gateway connecting AI agents to MCP, OpenAPI, and GraphQL integrations
Executor is an open-source integration layer that lets AI agents discover and call MCP servers, OpenAPI endpoints, GraphQL APIs, and custom JavaScript functions through one consistent interface. It offers local, self-hosted, and managed cloud deployments, with sandboxed execution, host-side secret injection, shared credentials, and per-tool safety policies.
Best for agent capabilities
Useful in agent tasks
Overview
When to use Executor
Executor is listed for Auth, Data, Code Execution workflows. Executor is an open-source integration layer that lets AI agents discover and call MCP servers, OpenAPI endpoints, GraphQL APIs, and custom JavaScript functions through one consistent interface. It offers local, self-hosted, and managed cloud deployments, with sandboxed execution, host-side secret injection, shared credentials, and per-tool safety policies. Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.
In 4agent's task model, the product maps to web extraction, code execution, workflow automation, authentication and secrets. That makes it a candidate for workflows that research the web, manage memory and knowledge, build and deploy software, communicate with users.
Integration checklist
- Access: confirm the oauth authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
- Client support: official or documented clients are listed for typescript.
- Automation: OpenAPI is listed as available, MCP is listed as available, and CLI support is listed as available. Confirm each requirement in the provider's current documentation.
- Operations: test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.
Sources and verification
Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.