Veo 3.1 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Google AI Studio API key for Veo 3.1. You can create one at https://aistudio.google.com/app/apikey |
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 |
|---|---|
| upload_imageA | Upload an image to Google Files API for use as reference, first frame, or last frame in video generation. Returns a fileUri that can be reused for 48 hours. This is the most token-efficient way to pass images to video generation. |
| start_video_generationA | Start a Veo 3.1 video generation job. This returns an operation ID immediately - use get_video_job to poll for completion. Supports text-to-video, reference images (up to 3), and first/last frame interpolation. |
| get_video_jobA | Check the status of a video generation job. Returns status and video URLs when complete. Videos are returned as download URLs - you can save them locally or share the links. |
| extend_videoB | Extend a Veo-generated video by additional seconds. Input video must be from a previous Veo generation (not an arbitrary video). |
| start_batch_video_generationA | Start multiple video generation jobs with controlled concurrency. Returns operation names for all jobs. Use this to generate multiple videos efficiently while respecting rate limits. |
| estimate_veo_costB | Estimate the cost in USD for a video generation request before starting it. Helps plan budgets and batch sizes. |
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 6 tools
Each tool has a clearly distinct purpose with no overlap: cost estimation, video extension, job status checking, batch generation, single generation, and image upload. The descriptions reinforce distinct workflows (e.g., 'extend_video' specifically requires Veo-generated input, while 'upload_image' handles image preparation).
All tools follow a consistent verb_noun pattern with snake_case (e.g., 'estimate_veo_cost', 'extend_video', 'get_video_job'). The naming is predictable and readable, using clear verbs like 'estimate', 'extend', 'get', 'start', and 'upload' paired with relevant nouns.
Six tools are well-scoped for a video generation server, covering core operations from initiation to status checking and cost management. This count avoids bloat while ensuring each tool earns its place, such as separate tools for single and batch generation to handle different use cases efficiently.
The toolset provides complete coverage for the video generation domain: starting jobs (single and batch), checking status, extending videos, uploading images for reference, and estimating costs. There are no obvious gaps; agents can handle the full lifecycle from planning to retrieval without dead ends.