Happy slice of mcp pizzaMCP.pizza

floom

MCP.Pizza Chef: floomhq

Floom lets you create and run AI-powered background workers that perform tasks repeatedly without needing your constant attention. You can deploy Python scripts or plain-English AI agents that run on schedules, webhooks, or manual triggers. Every run is logged and can require approvals, so you stay in control. It works with AI clients like Claude Code and Codex and connects through MCP or REST. Setup involves preparing simple worker folders and deploying them with commands—no complex coding needed.

Other

Use This MCP server To

Run AI tasks automatically on a schedule without manual intervention Deploy a Python script as a repeatable AI-powered background job Get daily digests or reports generated by AI workers Trigger AI workflows via webhooks or app events Review logs and outputs from past AI task runs Require approvals before AI workers perform side-effect actions

README

Floom

The loop engineering harness. AI workers that run on a loop.

Schedule them, trigger them, require approvals, and keep every run on the record.
A worker is a folder: worker.yml + SKILL.md or run.py. Deploy it from Claude Code, Codex, or the CLI. Run it from the UI, REST, or MCP.

Get started · Build a worker · Try the hosted version · Read the docs

CI Stars License Sandboxed by default Linux, macOS, Windows

Floom: the loop engineering harness for AI workers

Most "AI automation" is a chat window you babysit, or a no-code graph that bills you per task and can't be audited. Floom is the loop engineering harness: a real runtime where a worker is a readable package, it runs on a loop without you watching, and every execution leaves logs, outputs, tool calls, approvals, and a replay you can trust. Used natively from Claude Code and Codex via MCP or CLI.

Deploy A Python Script As An App, REST API, And MCP Tool

Floom lets an agent or developer turn a Python script into a worker that non-developers can run from a UI, other systems can call through REST, and AI agents can operate through MCP.

Start with three files:

workers/my-worker/
  worker.yml
  run.py
  requirements.txt

Then validate, deploy, and run:

floom workers validate ./workers/my-worker
floom workers push ./workers/my-worker
floom run my-worker --input key=value

Read BUILDING.md for the full copy-paste worker contract.

floom FAQ

Can I use this to schedule and run AI tasks automatically?
Yes — Floom lets you set up AI workers that run on schedules or triggers without manual babysitting.
Can I use this to run Python scripts as AI-powered background tasks?
Yes — you can deploy Python scripts as workers that run repeatedly and safely.
Which apps or AI clients work with Floom?
Floom integrates natively with Claude Code, Codex, and supports calls via MCP or REST interfaces.
Do I need an API key or special account to use Floom?
You don’t need an API key to run Floom itself, but you pay for the AI model usage separately (OpenAI, Claude, Gemini, etc).
How hard is it to set up Floom?
Setup is copy-paste-config level — you prepare worker folders and deploy them with simple commands.
Can I see logs and outputs of the AI workers?
Yes — every run is recorded with logs, outputs, tool calls, and approvals for full transparency.