Pack a coding agent harness into one MCP server you can drive from ChatGPT
A developer built CloudHarness MCP, a whole coding agent harness inside one MCP server: pi agents run inside it and carry out tasks delegated from ChatGPT, skills install from any GitHub repo, and credentials are injected without showing up in chat.
Source
@goon_nguyen on X · 2026-10-18
Written in our own words. Credit to the original author. Link checked 2026-10-19.
What they did
A developer built CloudHarness MCP, a whole coding agent harness inside one MCP server: pi agents run inside it and carry out tasks delegated from ChatGPT, skills install from any GitHub repo, and credentials are injected without showing up in chat.
Result (as claimed)
Runs on a $24/month Contabo VPS with 12 vCPUs and 48 GB RAM; open source under MIT.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up ChatGPT, Pi, Contabo. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Pack a coding agent harness into one MCP server you can drive from ChatGPT What the original author did: A developer built CloudHarness MCP, a whole coding agent harness inside one MCP server: pi agents run inside it and carry out tasks delegated from ChatGPT, skills install from any GitHub repo, and credentials are injected without showing up in chat. Reported result (as claimed by the author): Runs on a $24/month Contabo VPS with 12 vCPUs and 48 GB RAM; open source under MIT. Source: https://x.com/goon_nguyen/status/2111809276469789106 Tools they used: ChatGPT, Pi, Contabo Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Pack a coding agent harness into one MCP server you can drive from ChatGPT What the original author did: A developer built CloudHarness MCP, a whole coding agent harness inside one MCP server: pi agents run inside it and carry out tasks delegated from ChatGPT, skills install from any GitHub repo, and credentials are injected without showing up in chat. Reported result (as claimed by the author): Runs on a $24/month Contabo VPS with 12 vCPUs and 48 GB RAM; open source under MIT. Source: https://x.com/goon_nguyen/status/2111809276469789106 Tools they used: ChatGPT, Pi, Contabo Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Pack a coding agent harness into one MCP server you can drive from ChatGPT What the original author did: A developer built CloudHarness MCP, a whole coding agent harness inside one MCP server: pi agents run inside it and carry out tasks delegated from ChatGPT, skills install from any GitHub repo, and credentials are injected without showing up in chat. Reported result (as claimed by the author): Runs on a $24/month Contabo VPS with 12 vCPUs and 48 GB RAM; open source under MIT. Source: https://x.com/goon_nguyen/status/2111809276469789106 Tools they used: ChatGPT, Pi, Contabo Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to run multiple coding agents together · How to build an MCP server for AI agents · How to secure vibe-coded apps and agents · How to use Claude Code skills and plugins
Related use cases
Call any coding agent harness by name from one sandboxed server
He built an open-source server where you name the harness (Claude Code, Codex, Pi or about 20 more) and send a request, with each run sandboxed. Use it for one-off jobs, build agents on top, or write loops instead of prompts.
Swipe between your coding agent sessions in an iPhone app
A developer made an iOS app that flips between individual Claude Code, pi and other coding agent sessions with swipe gestures, and shows mockups right in the app instead of local or Tailscale links.
Run Claude Code, Codex, OpenCode and Pi in one workflow that ends in a pull request
Aqorin 0.3.0 is a TUI and CLI that gives each role its own runtime and model, sandboxes writes on macOS, lets your own checks decide when work passes, and turns a finished run into a pull request.
Add local-first memory to any LLM with Mnemo
Built Mnemo, a local-first AI memory layer for any LLM using Rust, SQLite and petgraph.