Deploy and supervise background AI workers that run on schedules, webhooks, or manual triggers with full audit logs and human-in-the-loop approvals.
Also known as floomhq/floom, @floomhq/mcp-server
- Stars
- 47
- Tools
- 32
- Downloads, 30 days
- 168
- Latest version
- 0.1.6
- Last commit
- Oct 2, 2026
- License
- MIT
What is Floom MCP?
Floom deploys and supervise background AI workers that run on schedules, webhooks, or manual triggers with full audit logs and human-in-the-loop approvals. It exposes 32 tools, such as deploy, run, list_projects.
Summary generated from the project's README
About Floom MCP server
Floom provides a runtime environment for deploying and supervising background AI workers. It is designed for engineers and operators who need to automate recurring knowledge work, such as inbox triage or daily digests, without relying on opaque chat threads or expensive no-code automation platforms. Users can build workers by organizing a folder containing a manifest file, a script like run.py, or a plain-English SKILL.md file.
Developers can deploy these workers using the CLI or through tools like Claude Code and Codex. The system supports various triggers including manual execution, cron schedules, webhooks, and Composio events. For security, script workers execute within E2B sandbox microVMs to ensure host isolation, while all side-effecting actions can be gated by human-in-the-loop approvals. The platform maintains a complete audit trail, recording every tool call, log, and output for replay or rollback purposes.
What you can do with it
- 1Automate recurring daily digestsCreate a scheduled worker that fetches GitHub pull requests and issues to generate a markdown summary every morning.
- 2Deploy Python scripts as managed toolsTransform a local Python script into a background worker accessible via a UI, REST API, or MCP.
- 3Ensure safe AI executionUse human approval gates to prevent AI agents from performing unauthorized side effects.
- 4Audit and replay agent actionsReview the exact tool calls and outputs of a previous worker run to verify its work.
Written from the project's README. Every use case is checked against a quote from it.
How to install Floom MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Floom MCP in Claude Code
$ claude mcp add --env 'FLOOM_API_KEY=<YOUR_FLOOM_API_KEY>' --env 'FLOOM_BASE_URL=<FLOOM_BASE_URL>' floom -- npx -y @floomhq/mcp-serverInstall Floom MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"floom": {
"command": "npx",
"args": [
"-y",
"@floomhq/mcp-server"
],
"env": {
"FLOOM_API_KEY": "<YOUR_FLOOM_API_KEY>",
"FLOOM_BASE_URL": "<FLOOM_BASE_URL>"
}
}
}
}Install Floom MCP in VS Code
.vscode/mcp.json
{
"servers": {
"floom": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@floomhq/mcp-server"
],
"env": {
"FLOOM_API_KEY": "<YOUR_FLOOM_API_KEY>",
"FLOOM_BASE_URL": "<FLOOM_BASE_URL>"
}
}
}
}Install Floom MCP in VS Code CLI
$ code --add-mcp '{"name":"floom","type":"stdio","command":"npx","args":["-y","@floomhq/mcp-server"],"env":{"FLOOM_API_KEY":"<YOUR_FLOOM_API_KEY>","FLOOM_BASE_URL":"<FLOOM_BASE_URL>"}}'Install Floom MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"floom": {
"command": "npx",
"args": [
"-y",
"@floomhq/mcp-server"
],
"env": {
"FLOOM_API_KEY": "<YOUR_FLOOM_API_KEY>",
"FLOOM_BASE_URL": "<FLOOM_BASE_URL>"
}
}
}
}Install Floom MCP in Codex
$ codex mcp add floom --env 'FLOOM_API_KEY=<YOUR_FLOOM_API_KEY>' --env 'FLOOM_BASE_URL=<FLOOM_BASE_URL>' -- npx -y @floomhq/mcp-serverInstall Floom MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.floom] command = "npx" args = ["-y", "@floomhq/mcp-server"] [mcp_servers.floom.env] FLOOM_API_KEY = "<YOUR_FLOOM_API_KEY>" FLOOM_BASE_URL = "<FLOOM_BASE_URL>"
Install Floom MCP in Gemini CLI
$ gemini mcp add -s user -e 'FLOOM_API_KEY=<YOUR_FLOOM_API_KEY>' -e 'FLOOM_BASE_URL=<FLOOM_BASE_URL>' floom npx -- -y @floomhq/mcp-serverInstall Floom MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"floom": {
"command": "npx",
"args": [
"-y",
"@floomhq/mcp-server"
],
"env": {
"FLOOM_API_KEY": "<YOUR_FLOOM_API_KEY>",
"FLOOM_BASE_URL": "<FLOOM_BASE_URL>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @floomhq/mcp-server 0.1.6 in an isolated container with no network and no keys. It answered and listed 32 tools.
Floom MCP tools 32
Read from the server with tools/listdeployDeploy Python code to Floom and get a usable URL. Accepts raw Python source or a base64-encoded ZIP. Optionally include a floom.yaml config to declare endpoint schemas, secrets, and resource requirements.
runExecute an action on a deployed Floom app. Preferred: use app_slug + action for simple invocation. Alternative: use project_id + endpoint_id + version_id for explicit control.
list_projectsList all deployed Floom projects.
get_projectGet details for a Floom project including endpoint schemas and input parameters. Use this before calling run to see what inputs an endpoint expects.
manage_secretsManage secrets for a Floom project. Supports list, set, and delete operations.
get_logsGet recent run logs for a Floom project.
list_versionsList all versions of a Floom project. Shows which version is dev (latest deploy) and which is prod (promoted).
promotePromote a version to production. By default promotes the current dev version. Runs a health check; auto-rolls back if the check fails.
rollbackRollback production to a previous version.
storage_setStore a persistent key-value pair for a Floom project. Values persist across runs and deploys.
storage_getRetrieve a stored value for a Floom project.
storage_deleteDelete a stored value for a Floom project.
| deploy | Deploy Python code to Floom and get a usable URL. Accepts raw Python source or a base64-encoded ZIP. Optionally include a floom.yaml config to declare endpoint schemas, secrets, and resource requirements. | |
| run | Execute an action on a deployed Floom app. Preferred: use app_slug + action for simple invocation. Alternative: use project_id + endpoint_id + version_id for explicit control. | |
| list_projects | List all deployed Floom projects. | |
| get_project | Get details for a Floom project including endpoint schemas and input parameters. Use this before calling run to see what inputs an endpoint expects. | |
| manage_secrets | Manage secrets for a Floom project. Supports list, set, and delete operations. | |
| get_logs | Get recent run logs for a Floom project. | |
| list_versions | List all versions of a Floom project. Shows which version is dev (latest deploy) and which is prod (promoted). | |
| promote | Promote a version to production. By default promotes the current dev version. Runs a health check; auto-rolls back if the check fails. | |
| rollback | Rollback production to a previous version. | |
| storage_set | Store a persistent key-value pair for a Floom project. Values persist across runs and deploys. | |
| storage_get | Retrieve a stored value for a Floom project. | |
| storage_delete | Delete a stored value for a Floom project. |
Show all 32 toolsShow fewer tools
storage_listList all stored keys for a Floom project with usage info.
create_share_linkCreate a public share link for a Floom endpoint. Share links allow anyone to run the endpoint without authentication.
list_share_linksList all share links for a Floom project.
disable_share_linkDisable a share link for a Floom project. The link will no longer be accessible.
fetch_contextFetch external data from a URL and attach it as context to a Floom project. Context data enhances AI-powered endpoints.
list_contextsList all context entries for a Floom project.
delete_contextRemove a context entry from a Floom project.
delete_projectDelete a Floom project and all its data (versions, runs, secrets, storage).
update_projectUpdate a Floom project name or slug.
deploy_from_githubDeploy a Floom app directly from a GitHub repository URL.
list_templatesList available starter templates for Floom projects.
get_templateGet details and code preview for a Floom starter template.
create_from_templateCreate a new Floom project from a starter template.
get_contextRetrieve stored context data for a Floom project.
refresh_contextRe-fetch context data from its source URL.
create_scheduleCreate a cron schedule that automatically runs an endpoint at specified intervals.
list_schedulesList all cron schedules for a Floom project.
delete_scheduleDelete a cron schedule from a Floom project.
enable_webhooksEnable public inbound webhooks for a Floom project. Once enabled, external services can trigger runs via POST /v1/webhooks/:slug/:action without authentication.
disable_webhooksDisable public inbound webhooks for a Floom project.
| storage_list | List all stored keys for a Floom project with usage info. | |
| create_share_link | Create a public share link for a Floom endpoint. Share links allow anyone to run the endpoint without authentication. | |
| list_share_links | List all share links for a Floom project. | |
| disable_share_link | Disable a share link for a Floom project. The link will no longer be accessible. | |
| fetch_context | Fetch external data from a URL and attach it as context to a Floom project. Context data enhances AI-powered endpoints. | |
| list_contexts | List all context entries for a Floom project. | |
| delete_context | Remove a context entry from a Floom project. | |
| delete_project | Delete a Floom project and all its data (versions, runs, secrets, storage). | |
| update_project | Update a Floom project name or slug. | |
| deploy_from_github | Deploy a Floom app directly from a GitHub repository URL. | |
| list_templates | List available starter templates for Floom projects. | |
| get_template | Get details and code preview for a Floom starter template. | |
| create_from_template | Create a new Floom project from a starter template. | |
| get_context | Retrieve stored context data for a Floom project. | |
| refresh_context | Re-fetch context data from its source URL. | |
| create_schedule | Create a cron schedule that automatically runs an endpoint at specified intervals. | |
| list_schedules | List all cron schedules for a Floom project. | |
| delete_schedule | Delete a cron schedule from a Floom project. | |
| enable_webhooks | Enable public inbound webhooks for a Floom project. Once enabled, external services can trigger runs via POST /v1/webhooks/:slug/:action without authentication. | |
| disable_webhooks | Disable public inbound webhooks for a Floom project. |
Configuration
FLOOM_API_KEYRequiredSecretAPI key for authenticating with Floom
FLOOM_BASE_URLRequiredBase URL of the Floom control plane
| Name | Description | |
|---|---|---|
| FLOOM_API_KEY | API key for authenticating with Floom | RequiredSecret |
| FLOOM_BASE_URL | Base URL of the Floom control plane | Required |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubMost "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.
What Floom Is: Worker Runtime For Background AI Workers
Floom turns repeatable knowledge-work automations into background AI workers. A worker can run manually, on a schedule, from a webhook, or from an app event. The runtime keeps the worker definition, input schema, output schema, logs, tool calls, approvals, and run history inspectable.
Use Floom when you want an AI agent to do recurring work without turning that work into an opaque chat thread, a hard-to-diff automation graph, or a one-off script with no supervision.
Build And Deploy An AI Worker From A Folder
AI agents and developers can build a Floom worker from a folder:
workers/<worker-id>/
worker.yml # manifest: inputs, outputs, trigger, runtime, secrets
run.py # script entrypoint, or SKILL.md for agent mode
requirements.txt # optional Python dependencies
Deploy the worker with:
floom workers validate ./workers/<worker-id>
floom workers push ./workers/<worker-id>
floom run <worker-id> --input key=value
After deployment, Floom exposes the worker in the UI, through REST endpoints, and through the Floom MCP server for AI clients. For the complete copy-paste build contract, read BUILDING.md.
What A Worker Looks Like
A worker is a folder-backed job definition. Describe the work in plain English (SKILL.md) or hand it a script (run.py), declare its tools, trigger, memory, and secrets in worker.yml, and Floom runs it.
# workers/github-digest/worker.yml (abbreviated)
name: github-digest
description: "Every morning at 9am, send a digest of unread GitHub PRs and open issues."
exec:
entry: SKILL.md # plain-English agent; or run.py for a script
trigger:
type: schedule
cron: "0 9 * * *" # also: manual, webhook, Composio event
connections:
- app: github # the only tools this agent is allowed to call
allowed_tools: [GITHUB_FIND_PULL_REQUESTS, GITHUB_LIST_ASSIGNED_ISSUES]
<!-- workers/github-digest/SKILL.md -->
You are a GitHub assistant generating a daily PR + issues digest.
Fetch the user's open PRs and assigned issues, compile a markdown digest
with Action items, and finish_with_outputs({ "digest": "<markdown>" }).
It runs at 9am, calls only the two GitHub tools it declared, and writes digest.md to a run you can open, replay, or roll back:
run 7f3a · github-digest · finished 09:00:04 · 2 tool calls · output: digest.md
✓ GITHUB_FIND_PULL_REQUESTS q="is:open is:pr author:@me" → 4 PRs
✓ GITHUB_LIST_ASSIGNED_ISSUES state=open → 2 issues
→ out/digest.md (text/markdown) [open · replay · rollback]
The full manifest adds schema_version, title, version, and declared outputs. See workers/ for runnable examples, BUILDING.md for a minimal deployable worker, and the agent cookbook.
Two kinds of agent
| runs in | host isolation | tools | side effects | |
|---|---|---|---|---|
Script (run.py / .sh / .js / .ts) |
E2B sandbox microVM | isolated filesystem, env & process; platform secrets withheld | sandbox + declared connections | approval gate when declared |
Agent (SKILL.md) |
AgentDriver in the API process (trusted bundles only) | not microVM-isolated by policy | declared connections, allow-listed | approval gate when declared |
Sandboxes allow public network egress by default and block private/internal ranges; a stricter allowlist is optional. Full trust model: ARCHITECTURE.md.
Worker Runtime At A Glance
| What it is | Self-hosted runtime to create, run, and supervise background AI agents |
| Best for | Recurring agent work: inbox triage, digests, outreach drafting, enrichment, monitoring |
| Agent types | Script (run.py/.sh/.js/.ts) and plain-English agent (SKILL.md) |
| Isolation | Script workers run in E2B sandbox microVMs - isolated host filesystem, env & process; platform secrets withheld |
| Triggers | Manual, schedule (cron), webhook, Composio event |
| Safety | Human-in-the-loop approvals for side-effecting agents; tools allow-listed per agent |
| On the record | Every run records logs, outputs, tool calls, approval state, replay + rollback |
| Cost model | Floom adds no per-task fee - you pay E2B sandbox runtime (per second) plus your model/API provider usage |
| Stack | Next.js + Tailwind UI · FastAPI + SQLite API · MCP server + CLI |
| Runs on | Linux, macOS, Windows (Python 3.11+, Node 20+) |
| License | MIT · hosted version |
Who Floom Is For
- Founders & operators turning recurring work (digests, triage, outreach) into agents that run themselves.
- Engineers who want a real runtime - manifests, sandboxes, limits, approvals - not a prompt file and a cron job.
- Teams who need every action allow-listed, approved, and replayable for audit.
- Anyone burned by agents that ran a destructive command, leaked a secret, or claimed success with nothing on the record.
Floom Compared: Raw Scripts vs Zapier vs Hand-Rolled MCP
| raw scripts | Zapier / Make | hand-rolled MCP server | Floom | |
|---|---|---|---|---|
| Worker definition | ad-hoc prompt or code | visual graph, hard to diff | custom tool server code | a folder: worker.yml + SKILL.md or run.py |
| Runtime | cron, shell, or local process | vendor automation runtime | whatever the developer builds | agent runtime with triggers, runs, logs, outputs, approvals, replay, and rollback |
| Isolation | runs on your host | vendor cloud, opaque | depends on implementation | E2B sandbox microVM for script workers |
| Tool access | whatever the script can reach | per-connector | MCP tools only | declared and allow-listed per worker |
| Side effects | fire immediately | workflow-dependent | custom approval logic | human approval gate when declared |
| Observability | scrollback, if any | per-step logs | custom logs | logs, tool calls, outputs, artifacts, approval state, replay, and rollback |
| Agent access | custom wrapper needed | not an agent-native build target | agent can call tools, but app runtime is separate | MCP tools let agents create, run, watch, and inspect workers |
| Cost model | model tokens and infrastructure | per-task or per-execution fees | model tokens and infrastructure | no per-task fee; you pay runtime and provider usage |
| Hosting | your host | vendor only | your host | self-host, or hosted |
Quick Start: Run Floom Locally
Linux / macOS
git clone https://github.com/floomhq/floom.git
cd floom
./scripts/setup.sh
# edit apps/api/.env: add a model provider key and E2B_API_KEY
./scripts/dev.sh
Windows PowerShell
git clone https://github.com/floomhq/floom.git; cd floom
.\scripts\setup.ps1
# edit apps\api\.env: add a model provider key and E2B_API_KEY
.\scripts\dev.ps1
Requires Python 3.11+, Node.js 20+, Git, a model provider key, and an E2B key from e2b.dev. Open http://localhost:3000 and sign in - no auth secret for local dev, and the example agents are seeded on first boot.
Full setup, model providers, optional integrations, and the safe self-hosting checklist: docs/GETTING-STARTED.md. Common issues: docs/TROUBLESHOOTING.md.
Not ready to self-host? floom.dev is the hosted version - hire AI agents with no setup. Hosted users can start from an MCP client with:
npx -y @floomhq/floom mcp install --target claude
The .env, model-provider, and E2B keys above are for running your own local or
self-hosted runtime, not for using Floom Cloud.
How a run works
Core concepts
- Agents - folders under
workers/<name>/withworker.ymlplus a script entrypoint (run.py) or an agent prompt (SKILL.md). - Runs - every execution records logs, outputs, tool calls, approval state, and replay/rollback context.
- Contexts - reusable file bundles attached to agents as reference material; sensitive by default.
- Approvals - side-effecting agents pause for a human decision before anything leaves the building.
- Workspace history - agents, contexts, and settings versioned in a git-backed workspace for rollback.
Write your first agent in docs/GETTING-STARTED.md, then docs/AUTHORING.md for the full manifest and runtime contract.
How workers execute
Script workers (.py/.sh/.js/.ts) run in an E2B sandbox microVM by default: isolated dependencies, no host process access, contained resources. TypeScript workers use the Node runtime with tsx (npx --yes tsx run.ts) and the same inputs.json/result.json contract as Python workers. A bundle that dumps os.environ inside the sandbox sees only sandbox metadata - FLOOM_SECRET, provider keys, and E2B_API_KEY are all absent. Agent workers (SKILL.md) run through the API-hosted AgentDriver tool loop and are governed by their declared connections and the approval gate; the current single-tenant policy permits only trusted agent bundles on that path. There is no in-process local script runner. Full trust model: ARCHITECTURE.md.
Data handling, connected-account safeguards, retention boundaries, and hosted Cloud legal surfaces are summarized in docs/DATA-RETENTION.md.
Architecture
apps/web Next.js + TypeScript + Tailwind + shadcn/ui
apps/api FastAPI + SQLite + Pydantic
apps/mcp MCP server + CLI
workers/ Worker folders (worker.yml + run.py or SKILL.md)
data/ SQLite DB + run artifacts
FAQ: AI Agents, MCP, And Deploying Python Scripts
What is Floom in one sentence?
Floom is an open-source runtime for background AI workers that run from versioned worker folders with declared inputs, outputs, triggers, tools, approvals, logs, REST API access, UI access, and MCP access.
Is Floom an MCP server?
Floom includes an MCP server, but it is more than an MCP server. The MCP endpoint lets agent clients create, run, watch, inspect, and manage Floom workers. The Floom runtime is the part that executes those workers, records runs, manages approvals, and exposes the UI and REST API.
Can an AI coding agent build a Floom worker from this repo?
Yes. Read BUILDING.md first. The build contract is a workers/<id>/ folder with worker.yml, run.py or SKILL.md, and optional requirements.txt, then floom workers validate and floom workers push.
Can I deploy a Python script as an app, REST API, and MCP-accessible worker?
Yes. Put the script in workers/<id>/run.py, declare its inputs and outputs in worker.yml, deploy it with floom workers push, and Floom makes it runnable from the UI, REST API, and MCP tools.
What is the difference between script mode and agent mode?
Script mode runs deterministic code such as Python, shell, or Node in the sandbox. Agent mode runs a SKILL.md prompt through the agent loop with declared tools and output writers.
Does Floom replace Zapier or Make?
Floom is for teams that want versioned worker folders, sandbox execution, approval gates, logs, outputs, replay, rollback, REST API access, and MCP access. Zapier and Make are visual automation products with their own vendor runtimes.
Does Floom replace hand-written MCP tools?
Floom can expose work through MCP without making you hand-roll the whole app runtime. A hand-written MCP server gives an agent tools; Floom gives the worker a runtime, UI, API, triggers, outputs, logs, approvals, and MCP tools.
Docs
- Getting started - why Floom exists, first run, first agent, safe self-hosting checklist.
- Building Floom workers - machine-readable build contract for agents and developers.
- Authoring agents - full
worker.ymlschema, execution modes, secrets, connections, triggers, approvals. - Data, retention, and safeguards - what Floom stores, how connected-account data is scoped, and what deletion/retention guarantees are safe to make.
- Agent cookbook - agent-assisted authoring recipes.
- Architecture - runtime topology and the sandbox trust model. Read before filing security findings.
- API overview - curated endpoint map; full reference at
http://localhost:8000/docs. - Troubleshooting · Roadmap · Project history · v1.0.0 release notes
- Licensing - Floom's MIT license and third-party dependency license notes.
Contributing
Contributions are welcome. See CONTRIBUTING.md for local setup, the first-contribution map, and PR guidelines. Quick local checks from the repo root:
npm run test:api
npm run lint:web
npm run test:web
npm run test:mcp
Security
To report a vulnerability, follow SECURITY.md and report it privately rather than opening a public issue.
License
MIT License (c) 2026 Floom contributors. You may use, copy, modify, merge, publish, distribute, sublicense, and sell copies of Floom, subject to the MIT license notice and warranty disclaimer.
Floom MCP questions
How do I add Floom MCP to Claude Code?
Run claude mcp add --env 'FLOOM_API_KEY=<YOUR_FLOOM_API_KEY>' --env 'FLOOM_BASE_URL=<FLOOM_BASE_URL>' floom -- npx -y @floomhq/mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add Floom MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Floom MCP provide?
It exposes 32 tools, including deploy, run, list_projects, get_project, manage_secrets.
What is Floom?
Floom is a loop engineering harness that provides a runtime for background AI workers to run without constant supervision.
How are script workers isolated?
Script workers run in E2B sandbox microVMs, which provide an isolated filesystem, environment, and process to ensure security.
Can I run workers on a schedule?
Yes, workers can be triggered manually, via a schedule (cron), webhooks, or Composio events.
Does Floom charge per task?
No, Floom does not charge a per-task fee; you only pay for your E2B sandbox runtime and your model/API provider usage.