Elena' s AI Blog

Connecting Codex CLI, Cursor, and Antigravity via MCP

02 Aug 2026 (updated: 28 Sep 2026) / 16 minutes to read

Elena Daehnhardt

 Generated by Midjourney. Prompt: Developer using Codex AI CLI in a dark terminal.


If you click an affiliate link and subsequently make a purchase, I will earn a small commission at no additional cost (you pay nothing extra). This is important for promoting tools I like and supporting my blogging.

I thoroughly check the affiliated products' functionality and use them myself to ensure high-quality content for my readers. Thank you very much for motivating me to write.



TL;DR:
  • Codex CLI, Cursor, and Antigravity can all call the same LangGraph orchestrator through one shared MCP server, instead of rebuilding Slack approval, file-writing, and retry logic per client.
  • Point `~/.codex/config.toml`, `.cursor/mcp.json`, and `~/.gemini/config/mcp_config.json` at the same server URL, e.g. `http://localhost:9000`.
  • MCP standardises tool discovery and invocation, so one server can serve multiple unrelated clients without custom integration code.

📚 This post is part of the "AI Orchestration" series

Series: AI Orchestration (Part 9 of 28)

Previous: Part 32 — Production Hardening: Idempotency, Run Isolation, and Crash Safety

Next: Part 13 — Build Your First MCP Tool: AI News Search and Newsletter in Python

Connecting Codex CLI, Cursor, and Antigravity via MCP

I’ve spent this series building an orchestration system almost nobody else could see: a worker model, a supervisor, a retry loop, a Slack approval gate, all wired into one LangGraph process I run from my own terminal. Useful, but lonely. Only my orchestrator ever called any of it.

Today that changes. I turn the system into something other tools can plug into: Codex CLI, Cursor, and Google’s Antigravity IDE, all talking to the same tool hub through the Model Context Protocol (MCP). MCP is an open protocol that lets any AI client discover and call tools exposed by a server, without a bespoke integration for each pairing. If you’ve been following along, you already have the orchestrator — this post is about wiring more clients into it, not rebuilding it.

MCP Hub Architecture: Centralising Tool Access for Multiple AI Clients

Instead of teaching every tool its own Slack logic, its own file-writing logic, its own retry logic, I centralise all of that behind one MCP server:

                ┌───────────────────────┐
                │     Codex CLI         │
                ├───────────────────────┤
                │       Cursor          │
                ├───────────────────────┤
                │     Antigravity       │
                └────────────▲──────────┘
                             │
                             │ MCP
                             │
                     ┌───────┴────────┐
                     │  MCP Tool Hub  │
                     │ (your tools)   │
                     └───────▲────────┘
                             │
                             │ tool boundary
                             │
                     ┌───────┴────────┐
                     │ LangGraph Core │
                     │ Orchestrator   │
                     └────────────────┘

The MCP hub exposes a small set of tools — write a file, request Slack approval, log an event — and anything that speaks MCP can call them. The orchestrator remains the brain. The MCP server becomes the one stable interface everything else talks to.

How MCP Messages Actually Travel Between Client and Hub

🔒 Subscribe to keep reading.

Why a Central MCP Hub Beats Per-Client Integrations

🔒 Subscribe to keep reading.

The Three MCP Roles: Orchestrator, Tool Hub, Client

🔒 Subscribe to keep reading.

Configuring MCP Servers in Codex CLI, Cursor, and Antigravity

🔒 Subscribe to keep reading.

What Trips People Up Once You Have Multiple MCP Servers

🔒 Subscribe to keep reading.

Why MCP Is the Correct Abstraction for Multi-Client Tool Access

🔒 Subscribe to keep reading.

MCP Mental Model: One Socket, Many Clients

🔒 Subscribe to keep reading.

MCP Client Setup Checklist

🔒 Subscribe to keep reading.

Three Things the Diagram Doesn’t Show

🔒 Subscribe to keep reading.

What Changes (and What Doesn’t) After Adding an MCP Hub

🔒 Subscribe to keep reading.

References

🔒 Subscribe to keep reading.

You've hit a Deep Dive tutorial.

I spend dozens of hours researching, coding, and breaking things to write these guides. This content is free, but reserved for my subscriber community. Drop your email below to unlock this guide (and all past/future deep dives):

Already a subscriber? Use the magic link from your last newsletter, or reset your password.

New subscribers get an inbox mail: Set a password to unlock articles. The form does not log you in — use the same email afterwards.

desktop bg dark

About Elena

Elena, a PhD in Computer Science, simplifies AI concepts and helps you use machine learning.



Citation
Elena Daehnhardt. (2026) 'Connecting Codex CLI, Cursor, and Antigravity via MCP', daehnhardt.com, 02 August 2026. Available at: https://daehnhardt.com/blog/2026/08/02/connecting-codex-cli-cursor-and-antigravity-via-mcp-to-langgraph/
All Posts
Copyright © Elena Daehnhardt
Privacy and Terms