---
title: "Executor Shrinks 278,800 AI Agent Tokens Down to 1,044 With One Tool"
subtitle: "Executor turns any OpenAPI, GraphQL, or MCP server into a single sandboxed tool call, cutting agent context bloat from 278k to 1k tokens."
url: "https://alphasignal.ai/news/executor-shrinks-278-800-ai-agent-tokens-down-to-1-044-with-one-tool"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-28T21:12:01.000Z"
updated: "2026-08-22T06:42:13.655Z"
type: "Repo"
topics:
  - "Agents"
  - "Open Source"
subtopics:
  - "Tool Use"
  - "Mcp"
  - "Agent Frameworks"
upvotes: 2792
source_url: "https://github.com/RhysSullivan/executor"
comments: 0
truncated: true
---

# Executor Shrinks 278,800 AI Agent Tokens Down to 1,044 With One Tool

> Executor turns any OpenAPI, GraphQL, or MCP server into a single sandboxed tool call, cutting agent context bloat from 278k to 1k tokens.

Anyone who has wired more than two integrations into an AI agent knows the pain: the same API keys pasted across Claude Code, Cursor, and ChatGPT, MCP servers configured three times over, and a system prompt that balloons past 250,000 tokens before the model even sees a user message. [Executor](https://github.com/UsefulSoftwareCo/executor) is an open-source MCP gateway that tries to collapse all of that into a single endpoint, and it just crossed 3,100 stars on GitHub.

[Executor](https://executor.sh) comes from Rhys Sullivan (of Answer Overflow fame) and is backed by Y Combinator. It's MIT licensed, written in TypeScript on a Bun + Turborepo monorepo, and ships as a CLI, a desktop app, a Docker image, a Cloudflare Worker, or a hosted cloud service. All of them share the same runtime.

## Token bloat, quantified

The headline claim is aggressive. Without Executor, a typical enterprise catalog of 1,640 tools across GitHub, Stripe, Jira, Sentry, Linear, Gmail, Notion, and Slack consumes around 278,800 tokens in the system prompt. With Executor, the model sees a single tool consuming roughly 1,044 tokens.

The trick is what the team calls code-mode MCP. Rather than exposing 1,640 individual schemas, Executor exposes one `execute` tool that runs TypeScript in a sandbox. The agent writes code that searches the catalog, describes only the tools it needs, and calls them:

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [RhysSullivan/executor (now UsefulSoftwareCo/executor) on GitHub](https://github.com/UsefulSoftwareCo/executor)
- [Executor — The gateway to connect your agent to everything](https://executor.sh)
- [Executor Documentation](https://executor.sh/docs)