Skip to main content
Glama
Sign In
@runapi.ai/veo-3-1-mcp

@runapi.ai/veo-3-1-mcp

by runapi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Why This Package?

@runapi.ai/veo-3-1-mcp is a focused Model Context Protocol server for the Veo 3.1 model line on RunAPI. It gives MCP-compatible assistants direct access to 3 endpoints and 3 model variants without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to Veo 3.1. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.

Related MCP server: veo-mcp-server

Install

Add it to Claude Code:

claude mcp add veo-3-1 -s user -- npx -y @runapi.ai/veo-3-1-mcp

Use project scope when the server should be shared with a repository:

claude mcp add veo-3-1 -s project -- npx -y @runapi.ai/veo-3-1-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "veo-3-1": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/veo-3-1-mcp"]
    }
  }
}

check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.

Tools

Tool

Auth

Purpose

extend_video

Yes

Create a Veo 3.1 extend video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

text_to_video

Yes

Create a Veo 3.1 text to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

upscale_video

Yes

Create a Veo 3.1 upscale video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

get_task

Yes

Fetch the current status and latest payload for an existing task.

check_pricing

No

Look up current pricing for a Veo 3.1 model and endpoint.

Models

Veo 3.1 covers 3 model variants across 3 endpoints. Each tool accepts the models listed for it:

Tool

Models

extend_video

no model parameter

text_to_video

veo-3.1, veo-3.1-fast, veo-3.1-lite

upscale_video

no model parameter

Model availability can change between releases. Use check_pricing or the Veo 3.1 model page for the current catalog view.

Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

Run a Veo 3.1 extend video task with RunAPI.

The assistant can call check_pricing, then extend_video, and return the task id, status, and output URLs.

Submit without waiting

Create the task but don't wait for it to finish.

The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.

Check pricing before creating

Check current Veo 3.1 pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the Veo 3.1 model page for the canonical catalog entry.

Configuration

The server resolves auth in this order:

  1. RUNAPI_API_KEY environment variable, useful for headless and CI hosts

  2. ~/.config/runapi/config.json, created by the MCP login tool or runapi login

  3. No key, which still allows check_pricing

The config file is normally managed by login. A pre-provisioned headless config can use:

{
  "apiKey": "your_runapi_key"
}

Do not commit real API keys.

Links

Resource

URL

Veo 3.1 model page

https://runapi.ai/models/veo-3.1

npm package

@runapi.ai/veo-3-1-mcp

GitHub repository

runapi-ai/veo-3-1-mcp

RunAPI MCP overview

runapi.ai/mcp

RunAPI docs

runapi.ai/docs

License

Licensed under the Apache License, Version 2.0.

Available Tools

6 tools
check_pricingC

Look up RunAPI pricing for the veo-3-1 model line.

Inputs: model, action.

extend_videoB

Create a Veo 3.1 task on RunAPI (extend video). Returns a task id, status, and output URLs.

Inputs: source_task_id (required), wait, seeds, prompt, +4 more.

get_taskB

Fetch the current status and latest result payload for a veo-3-1 task.

Inputs: action (required), task_id (required).

loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

Inputs: force.

text_to_videoC

Create a Veo 3.1 task on RunAPI (text to video). Returns a task id, status, and output URLs.

Inputs: wait, model, seeds, prompt, +11 more.

upscale_videoC

Create a Veo 3.1 task on RunAPI (upscale video). Returns a task id, status, and output URLs.

Inputs: wait, index, timeout_ms, callback_url, +3 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a clearly distinct action: authentication (login), pricing lookup (check_pricing), task submission for three different video operations, and task polling (get_task). Although upscale_video, extend_video, and text_to_video all wrap the same RunAPI task-creation mechanism, their names and descriptions make the operation each performs unambiguous.

    Naming Consistency4/5

    The set predominantly follows a snake_case verb_noun pattern (upscale_video, extend_video, text_to_video, get_task, check_pricing). The bare 'login' verb is a minor deviation but still readable and conventional for auth.

    Tool Count5/5

    Six tools is a well-scoped set for a single-model video generation wrapper, with each tool earning its place (auth, three generation modes, task status, pricing). Nothing feels redundant or missing at the count level.

    Completeness4/5

    Core lifecycle is covered: authenticate, submit a task, and poll its status/result. Minor gaps exist, such as no task listing/cancellation and no image-to-video variant if the model line supports it, but agents can work around these using get_task and the returned output URLs.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers