Floom

by floomhq

221 downloads
Not rated
GitHub

Description

<div align="center"> <img src="./docs/assets/hero-landing.png" alt="Floom" width="900" /> <h1>Floom</h1> <p><strong>The protocol + runtime for agentic work.</strong><br/> <em>Vibe-coding speed. Production-grade safety.</em><br/> Build agents, workflows, and scripts with AI…

About

<div align="center"> <img src="./docs/assets/hero-landing.png" alt="Floom" width="900" /> <h1>Floom</h1> <p><strong>The protocol + runtime for agentic work.</strong><br/> <em>Vibe-coding speed. Production-grade safety.</em><br/> Build agents, workflows, and scripts with AI. Floom deploys them as an MCP server, HTTP…

Details

Author
floomhq
Downloads
221
Categories
Developer Tools, Infrastructure, Cloud Service, Automation, Other

- One manifest generates a web form, MCP server, and HTTP API.
- Proxied mode wraps any existing API; hosted mode runs your Docker container.
- Built‑in Bearer/API‑key auth, per‑operation rate limits, and secret injection.
- Every app exposes MCP tools; four MCP admin tools let an agent add new apps.
- Shareable result URLs and run history are included out of the box.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Floom
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Point Floom at an OpenAPI spec URL. For the cloud version, sign in at floom.dev and publish via the build page. For self‑hosting, create an apps.yaml manifest and run the official Docker image with docker run; the manifest defines proxied (wrapping an existing API) or hosted (Floom runs your container) modes. Every published app is immediately available as a web form at /p/:slug, an MCP endpoint at /mcp/app/:slug, and an HTTP endpoint at /api/:slug/run.

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. If your code makes HTTP requests (requests, httpx, urllib), set config.network to true. Without it, outbound network access is blocked.

run

Execute an action on a deployed Floom app. Returns the function output as JSON. Preferred: use app_slug + action for simple invocation. Alternative: use project_id + endpoint_id + version_id for explicit control. Pass secrets: {KEY: value} for functions that require API keys.

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 persistent secrets (API keys, tokens) for a Floom project. Available across all runs. Supports list, set, and delete operations. For one-time secrets, use the secrets parameter on the run tool instead.

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.

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "floom": {
            "floom": {
                "command": "npx",
                "args": [
                    "-y",
                    "@floomhq/mcp-server"
                ]
            }
        }
    }
}

McpServers

{
    "floom": {
        "command": "npx",
        "args": [
            "-y",
            "@floomhq/mcp-server"
        ]
    }
}

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.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.