Executor

Founded by Rhys Sullivan in 2026

Connect AI agents to all your tools through one MCP gateway

Cost

Free Tier, Paid

Rating

★ People love it

Time to value

Quick Setup (< 1 hour)

You can use Executor to connect AI agents like Claude Code, Cursor, or Codex to all your existing tools through a single endpoint. It converts tools from different protocols (MCP, OpenAPI, GraphQL) into one uniform shape so any agent can call them the same way. It reduces token usage by only loading tool schemas when actually needed, keeps credentials secure in a sandboxed environment, and lets your whole team share integrations without per-person setup.

What Executor does

Register an OpenAPI, MCP, or GraphQL tool so any agent can call it with the same schemaSearch the tool catalog by query and load the schema only when a tool is actually neededInject API credentials into outbound requests without exposing them to the agent or modelReview a full trace of every tool call an agent made in a given runSet destructive action policies so agents ask before running mutations or deletesShare integrations and credentials across an entire team from a single configurationRun Executor as a background CLI service in a headless server environmentDeploy a self-hosted Executor instance for teams with custom security requirementsExposes a single 'execute' tool to agents instead of thousands, reducing prompt token usage by over 99%Normalizes MCP, OpenAPI, and GraphQL tools into one unified name-and-schema formatRuns tool calls in an isolated JavaScript sandbox so credentials never appear in agent or model contextAutomatically distinguishes safe (read) vs destructive (write/delete) actions and asks for confirmation before running dangerous onesShared team integrations with per-user and shared credentials — no per-person setup requiredFull trace log of every agent run and tool call for auditing decisions after the factAvailable as a cloud service, desktop app (Mac/Windows/Linux), or self-hosted CLI — all MIT licensedLazy-loads tool schemas only when actually called, keeping context windows small

Pricing breakdown

PlanPrice10 seats / yr

Team$150.00 / mo$18,000

Enterprise$0—

Annual estimates assume continuous billing at the listed list price. Volume discounts typical above 50 seats.

Frequently asked

Google calendar Stripe

Dex

Google Workspace OpenAI

OpenAI

GraphQL

laŭ

Want a tailored answer?

See whether Executor fits your stack.

Techbible weighs Executor against what you already pay for, your team shape, and the work that's actually happening. Free to start.

More in AI Orchestration and MLOps

All tools →

A visual AI playground

Tersa is an open source canvas for building AI workflows. Drag, drop connect and run nodes to build your own workflows powered by various industry-leading AI models.

AI Reliability for Production LLMs

Latitude is the reliability layer for AI products: detect failures, measure performance, and automatically improve model quality

AIMLAPI

AI API service providing easy access to over 200 AI models.

AMESA

Build and deploy AI agents to automate complex industrial processes.

Adaption

Build adaptive AI that learns continuously from your data

Agenta

Agenta is an open-source platform for building robust LLM Application. It provides tools for prompt engineering, evaluation, debugging, and monitoring of complex LLM Apps.

Agentic Fabriq

A security and identity layer that manages permissions, authentication, and governance for AI agents acting across enterprise tools.

Archestra

Enterprise MCP platform with security guardrails, compliance controls, and a curated catalog of 900+ evaluated Model Context Protocol servers for AI agents.