Skip to main content
Glama

genrelay-mcp

npm license

MCP server for GenRelay — generate video and images from Claude Desktop, Cursor, or any MCP client.

One server, several models: Veo 3.1, Grok Imagine, Omni Flash, Nano Banana Pro/2, GPT Image 2.

Sample outputs

Install

Nothing to install — point your MCP client at it with npx.

Claude Desktop — claude_desktop_config.json:

{
  "mcpServers": {
    "genrelay": {
      "command": "npx",
      "args": ["-y", "genrelay-mcp"],
      "env": { "GENRELAY_API_KEY": "sk-..." }
    }
  }
}

Cursor — .cursor/mcp.json:

{
  "mcpServers": {
    "genrelay": {
      "command": "npx",
      "args": ["-y", "genrelay-mcp"],
      "env": { "GENRELAY_API_KEY": "sk-..." }
    }
  }
}

Get a key at genrelay.ai. Restart the client after editing the config.

Related MCP server: Grok Imagine Video MCP Server

Tools

Tool

What it does

generate_video

Text-to-video and image-to-video. Returns the clip, or a task id if it's still running

generate_image

Image generation and editing. Returns the picture inline

check_job

Pick up a job by task id

list_models

What's available and what each model is for

Then just ask:

Generate an 8-second video of a neon fox running through a rainy city at night, 1080p

About the wait

Video generation takes 1–5 minutes — longer than an MCP tool call is allowed to run. So generate_video waits as long as it safely can, then hands back a task id:

Still generating — this is normal for video.

task id: task_abc123
status: in_progress
progress: 35%

Call check_job with task id "task_abc123" in a minute or two.

That's a normal outcome, not a failure. The job keeps running server-side — use check_job, don't resubmit (resubmitting bills a second time).

Images usually finish inside the budget and come back inline.

Models

Video

Model

Notes

veo_3_1

Google Veo 3.1 — highest quality, with audio

veo_3_1-fl

first/last frame — supply both endpoints

veo_3_1-components

component-guided

grok-imagine-video-1-5-preview

xAI Grok Imagine 1.5

grok-imagine-1-0-video

xAI Grok Imagine 1.0

omni-flash

fast, good for longer clips

omni_flash_abra_edit

video editing from a source video

Image — nano-banana-pro, nano-banana-2, gpt-image-2

Tiers: images 1k/2k/4k, Veo video 720p/1080p/4k. Pricing is per tier, and a size matching no tier falls back to the model's base rate — so set tier explicitly when cost matters.

Configuration

Variable

GENRELAY_API_KEY

required

GENRELAY_BASE_URL

optional, defaults to https://genrelay.ai/v1

Also available

Development

npm install
npm run build
node test/smoke.mjs   # boots the server and speaks MCP to it

FAQ

What is genrelay-mcp? An MCP server that lets Claude Desktop, Cursor and other MCP clients generate video and images through the GenRelay API.

Which clients work? Any MCP client that can launch a stdio server with npx -y genrelay-mcp, including Claude Desktop and Cursor.

How do I get an API key? Sign up at genrelay.ai and create a key in the console. Set it as GENRELAY_API_KEY.

How is it billed? Prepaid credits in USD, pay as you go. See Pricing.

A video is still running. Do I resubmit? No. Use check_job with the task id. Resubmitting is billed again.

Where is it listed? npm and the official MCP Registry as io.github.gaoruitech/genrelay-mcp.

License

MIT

Available Tools

4 tools
check_jobCheck a generation jobA

Check a job started earlier by generate_video or generate_image, using its task id. Returns the current status and, once finished, the download URL.

Inputs: task_id (required).

generate_imageGenerate an imageA

Generate an image with Nano Banana Pro/2 or GPT Image 2. Usually finishes within the tool-call budget and returns the picture inline. Supports image editing and reference-guided generation via reference_images.

Inputs: prompt (required), size, tier, model, +1 more.

generate_videoGenerate a videoA

Generate a video with Veo 3.1, Grok Imagine or Omni Flash. Generation usually takes 1-5 minutes, longer than a tool call can wait — if it is still running when the wait budget runs out, this returns a task id to check later with check_job. Supports text-to-video and image-to-video (pass reference_images).

Inputs: prompt (required), size, tier, model, +2 more.

list_modelsList available modelsA

List the video and image models this server can generate with, and what each is for.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct responsibility: generating video, generating images, checking async job status, and listing models. There is no meaningful overlap between any pair of tools.

    Naming Consistency5/5

    All tools follow the same snake_case verb_noun pattern: generate_video, generate_image, check_job, list_models. The naming is uniform and predictable.

    Tool Count5/5

    Four tools is well-scoped for a media generation relay: two generation entry points, one async status check, and one model discovery tool. Each tool earns its place without bloat or thinness.

    Completeness4/5

    The core workflow is covered: list available models, start generation, and poll async results. A cancellation or retry tool would make the lifecycle more complete, but it is not an obvious blocker for the stated purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers