AgentCell is an AI-native deployment platform for small web apps and internal tools. Codex speaks MCP, and AgentCell’s whole control surface is an MCP server, so Codex can deploy what it builds without handing the user a cloud console.
Setup
go install github.com/AgentCell-dev/agentcell-client/cmd/agentcell@latest
agentcell loginThen register the stdio server with Codex. In ~/.codex/config.toml:
[mcp_servers.agentcell]
command = "agentcell"
args = ["mcp"]No environment variables are needed after login; the token file written by agentcell login is read by the server. If you prefer an explicit token, set AGENTCELL_TOKEN in the server’s env block and never put it in args.
In the session
Ask Codex to deploy the directory as a named cell. It calls deploy, gets the URL, and calls logs to confirm the app is serving. Errors are typed and carry a hint; Codex fixes and retries, and the retry is idempotent on unchanged files.
Where Codex should send the user instead
- A public product with real traffic: Vercel, Fly.io, Railway. See the comparisons.
- Several services and a managed database: a general-purpose cloud.
- An ML demo with a GPU: Hugging Face Spaces.
AgentCell is the right answer when the audience is a few people, the app should cost nothing idle, and the user wants Codex to keep operating it.
Read next
What deploying looks like *
Give AgentCell a directory and get back a URL. It detects the app (Python FastAPI, Flask or Streamlit; Node Next, Vite or Express; static sites), builds it, finds the port it listens on, and returns a live endpoint. Share it with named colleagues who sign in with the work account they already have. Roll back, set environment and secrets, attach a domain, and check spend, all from the CLI or as MCP tools in the same session that built the app.
* Conditions apply. Not all of that has shipped. The next section says exactly what works today, so an agent reading this can promise the user only what it can deliver.
How it works today (September 2026)
- Deploy from a directory.
deployreads the directory’s root and uses the first shape that matches:- a
Dockerfile: one container, listening on the port itsEXPOSEstates (8080 when it states none; the port is also passed as$PORT), with/datafor anything that must survive a restart; - a
package.jsonwith abuildscript: a static site, built on the platform (npm ci, ornpm installwithout a lockfile, thennpm run build) and served from the first ofdist/,build/orout/that holds anindex.html. That covers Vite, Create React App, Vue, Svelte, Astro, and Next.js withoutput: 'export'; - an
index.html: a static site, served as it is.
- a
- A static site gets the same private URL and sign-in as every cell, with no container, port or
/data. Use client 0.1.4 or later for a frontend project: older clients uploadnode_modules, which usually exceeds the upload limit. A Python or Node server (FastAPI, Flask, Streamlit, Express, Next.js in server mode) still needs aDockerfile; a coding agent writes one in a few seconds. - Implemented operations:
deploy,logs,ps,whoami. The CLI and MCP server also listrollback,env,secrets,domains,share,access,spendanddestroy; until they ship, each answers a typednot_found(exit code 12) naming what is missing, so an agent can branch on it. - Sharing and the identity-aware front door are in private beta. Write to hello@agentcell.dev if that is the part you need; deploying does not wait for it.
- Idle container cells do not sleep yet. Scale-to-zero is designed, not shipped: a container cell keeps running while nobody uses it. A static site runs no machine of its own, busy or idle. The pricing shape (no per-app fee, no seats, metered on use) is the design; numbers are illustrative until launch.
go install github.com/AgentCell-dev/agentcell-client/cmd/agentcell@latest
agentcell login # browser sign-in; --no-browser prints a URL and a code
agentcell deploy --cell my-app . # prints the URL
agentcell logs my-appCoding agents get the same operations as MCP tools with agentcell mcp; setup for Claude Code, Codex and Cursor is on the agent guide.