Machine Learning

Google Veo MCP Server

Connect your account, then chat with AI to run tools.

Generate short clips from a prompt or still image, extend an existing Veo video, and download finished MP4s from chat — connect Google Veo in MCPBundles with your Google AI Studio access.

Best forContent CreatorsSocial MediaBrand MarketersCreative Ops

Try this workflow

Product hero clip

Generate an 8-second Google Veo video for Bright Smile Co — a calm dental office reception, slow dolly-in, warm morning light, soft ambient sound, no on-screen text.

Start chatting
Managed
9 tools
Agent guide included

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

What you can do with Google Veo

Built for

Content Creators, Social Media Teams, Brand Marketers, Creative Ops, Performance Marketing Teams

Example workflows

Product hero clip

Text-to-video brief with scene, camera, and audio direction.

Try this

Generate an 8-second Google Veo video for Bright Smile Co — a calm dental office reception, slow dolly-in, warm morning light, soft ambient sound, no on-screen text.

Animate a still

Image-to-video when marketing already has approved photography.

Try this

Turn this Harbor Legal team photo into a subtle motion clip — gentle parallax, office background slightly out of focus, professional tone for a LinkedIn post.

Extend a prior clip

Continuation workflow for slightly longer social cuts.

Try this

Extend the Riverside Dental Veo clip we generated yesterday by about seven more seconds — continue the same camera move and keep the subject walking toward the front desk.

Track generation status

Poll-and-download path so creators aren't stuck refreshing queues.

Try this

Check my in-progress Google Veo jobs, tell me which finished, and download the latest Acme Dental product demo as an MP4 I can share.

Context to know first

What is Google Veo MCP?

Google Veo MCP connects Google's Veo video models to AI assistants so you can generate short clips from prompts or images, extend prior Veo videos, and download finished MP4s from chat after you connect Google Veo in MCPBundles with your Google AI Studio access.

Who is this for?

Marketing and creative teams who need fast social clips, ad tests, and storyboard-style motion without opening a separate video tool for every variation.

What kinds of videos can I create?

Text-to-video from a written scene brief, image-to-video from a still frame, reference-guided looks on supported models, transitions between first and last frames, and extensions of clips Veo generated earlier.

Related editorial

Google Veo Video Workflows with AI

How AI agents can generate short clips from prompts or stills, extend prior Veo renders, and download MP4s for social and ad drafts.

Read article

AI Skill
SKILL.md

Domain knowledge for Google Veo — workflow patterns, data models, and gotchas for your AI agent.

Google Veo

Google Veo generates high-fidelity 8-second videos (720p / 1080p / 4k) with natively generated audio from text prompts or images.

Workflow

  1. Submit a generation request (text, image, references, frames, or extension). Returns an operation handle.
  2. Poll the operation every 10-15 seconds until status is completed and a video URI is present.
  3. Download through MCPBundles — the platform fetches the MP4 from Google and returns a presigned S3 link with clickable markdown for the user.

Generation modes

ModeWhen to use
Text-to-videoPrompt-only cinematic clip
Image first frameAnimate a still into motion
Reference images (1-3)Style and subject guidance on Veo 3.1
First + last frameControlled transition between two stills
Extend prior clipContinue a Veo-generated video (~7s more)

Data Model

  • Operations — long-running handles with done flag, progress metadata, and final generateVideoResponse containing generatedSamples[].video.uri.

Models

  • veo-3.1-generate-preview — latest, best quality, reference images, frame transitions, extension, 4k
  • veo-3.1-fast-generate-preview — lower latency 3.1 variant
  • veo-3.0-fast-generate-001 — lower latency, slightly reduced quality
  • veo-3.0-generate-001 — previous generation, good quality

Prompting

  • Include scene composition, camera movement, lighting, dialogue, and sound effects
  • Use negative prompts to exclude artifacts (e.g. "blurry, text overlays, distorted faces")
  • Max prompt length: 2000 characters

Gotchas

  • Invalid keys surface as API_KEY_INVALID on every upstream call — save-time validation should catch this after the provider update ships.
  • Async only: Every generation is asynchronous — always poll the operation.
  • Download: Raw video_uri values require the Gemini API key on the wire; use the platform download path so the user gets an S3 presigned MP4 link.
  • Resolution/latency tradeoff: 4k takes significantly longer than 720p.
  • Video extension is 720p only; input video must be from a prior Veo generation (stored ~2 days).
  • Reference images require Veo 3.1, 8-second duration, and must not be combined with first/last frame images in the same request.
  • First + last frame requires both images and 8-second duration; do not combine with reference images.
  • Image-to-video: starting image uses Vertex bytesBase64Encoded + mimeType on the instance, not Gemini inlineData.
  • Quota: Veo preview models have tight per-project limits; HTTP 429 means auth worked but quota is exhausted.

Tools in this Server (9)

Download Google Video

Download a completed Google Veo video. Fetches the file from Google using your API key, stores it in MCPBundles S3, and returns a presigned download_u...

Extend Google Video

Extend a Veo-generated video by ~7 seconds using its video_uri from a prior completed operation. Input must be Veo output (not arbitrary URLs). Return...

Generate Google Image To Video

Generate video from an image using Google Veo. The provided image becomes the first frame and the prompt describes the motion and story. Returns an op...

Generate Google Video

Generate video from a text prompt using Google Veo. Returns an operation ID — video generation is asynchronous and typically takes 1-3 minutes. Poll o...

Generate Google Video Frames

Generate video that transitions from a first-frame image to a last-frame image (Veo 3.1). Both images are required; duration must be 8 seconds. Return...

Generate Google Video References

Generate video from a text prompt plus up to three reference images (Veo 3.1). Reference images guide style and subject — omit first/last frame images...

Get Google Operation

Check the status of a Google Veo video generation operation. If the video is still processing, returns status 'processing'. If complete, returns the v...

List Google Models

List Google Gemini API models available to your API key. Use to confirm the key is valid and to discover supported Veo model names.

List Google Operations

List recent Google Veo video generation operations. Returns operation IDs, status, model, and video URIs for completed jobs. Use to find past generati...

Frequently Asked Questions

What is Google Veo MCP?

Google Veo MCP connects Google's Veo video models to AI assistants so you can generate short clips from prompts or images, extend prior Veo videos, and download finished MP4s from chat after you connect Google Veo in MCPBundles with your Google AI Studio access.

Who is this for?

Marketing and creative teams who need fast social clips, ad tests, and storyboard-style motion without opening a separate video tool for every variation.

What kinds of videos can I create?

Text-to-video from a written scene brief, image-to-video from a still frame, reference-guided looks on supported models, transitions between first and last frames, and extensions of clips Veo generated earlier.

How long does generation take?

Most clips are asynchronous — the assistant submits the job, checks progress until the render completes, then returns a downloadable MP4. Higher resolutions take longer; 720p is the fastest default for drafts.

How do I connect?

Open the Google Veo skill page in MCPBundles and add the access from Google AI Studio shown in your Google account setup. Usage follows your Google AI Studio project limits for Veo preview models.

How do I connect Google Veo to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/google-veo. Authentication is handled automatically.

How many tools does Google Veo provide?

Google Veo provides 9 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Google Veo require?

Google Veo uses API Key. Google Veo requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect Google Veo to any MCP client in minutes

MCP URL
https://mcp.mcpbundles.com/bundle/google-veo
Claude.aiCursorVS CodeVS Code InsidersGooseLM StudioCherry StudioChatGPT

One-click install:

Install on Claude.aiInstall for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

  1. Open claude.ai → Settings → Connectors.
  2. Click the + button and choose Add custom connector.
  3. Set Name to Google Veo and paste the MCP URL into Remote MCP server URL.
  4. Click Add. Google Veo will appear under Not connected — select it and click Connect to complete OAuth.
Name: Google Veo
Remote MCP server URL: https://mcp.mcpbundles.com/bundle/google-veo
Authentication: OAuth

Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).

Related MCP Servers

More machine learning integrations you might like

Originality.AI

Originality.AI is a content detection platform that identifies AI-generated text and checks for plag...

6 tools
Machine Learning
Minitap

Minitap is an AI model router and aggregation platform. Access 200+ language models through a unifie...

14 tools
Machine Learning
Yutori

Yutori builds reliable web agents that autonomously execute tasks on the web. Offers four APIs: n1 (...

15 tools
Machine Learning
FAL AI

FAL AI is a machine learning platform specializing in image and video generation through AI models. ...

40 tools
Machine Learning
ElevenLabs

ElevenLabs is an AI voice generation platform that creates realistic speech from text using advanced...

14 tools
Machine Learning
Runway

Runway provides AI-powered content generation APIs for creating images, videos, and other media. Gen...

18 tools
Machine Learning

Ready to use Google Veo?

Sign in to connect your credentials and start running tools from the chat.

Google Veo MCP Server — AI Video Workflows for Agents