autoflow-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| autoflow_statusA | Check the connection status of the Autoflow Chrome Extension and Google Flow tab. |
| autoflow_open_flowA | Instruct the Autoflow extension to open Google Flow (https://flow.google.com/) in an active browser tab. |
| autoflow_get_queueA | Inspect the current status of the Autoflow sequential job queue (active job, pending jobs, and recent history). |
| autoflow_generateA | Generate an AI video or image on Google Flow using Veo 3 or Nano Banana models via the Autoflow extension (queued sequentially). |
| autoflow_list_charactersB | Scan and list all available character tags in the currently open Google Flow project. |
| autoflow_capture_screenshotA | Capture a visual JPEG screenshot of the Google Flow project workspace so the AI agent can inspect progress, verify visual output, or diagnose UI state. |
| autoflow_get_recent_assetsA | Scan and list all recent video and image generation assets produced on the Google Flow project canvas. |
| autoflow_heal_flowA | Trigger self-healing: automatically detect and dismiss any blocking Google Flow error dialogs, rate limit popups, or warning snackbars. |
| autoflow_reload_tabA | Force-reload the Google Flow project tab and re-mount the extension bridge if the web app appears frozen or unresponsive. |
| autoflow_clear_queueA | Clear all pending queued generation jobs. |
| autoflow_cancelB | Cancel any running or queued generation job in Google Flow. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool targets a distinct action: status, generation, queue management, troubleshooting, and inspection. The only slight overlap is between clear_queue and cancel, but they differ in scope (clearing all pending vs. canceling any running/queued job). All others are clearly separated.
Tools follow a consistent 'autoflow_' prefix with verb-noun patterns like get_recent_assets, clear_queue, and capture_screenshot. However, 'autoflow_status' uses a noun instead of a verb, and there's a mix of 'get_' and 'list_' prefixes, which is a minor deviation.
11 tools is well-scoped for a specialized server focused on AI generation management in Google Flow. Each tool covers a distinct need without redundancy, and the count feels appropriate for the domain.
The tool surface covers the core lifecycle: generation, queue inspection/control, troubleshooting (heal/reload), and visual verification (screenshot). Minor gaps exist like asset management or project editing, but the essential workflows are complete.