Log inSubmit server
Hailuo MCP logo

Hailuo MCP

Run Hailuo video-generation tasks through RunAPI, poll results, and inspect model pricing over MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Hailuo MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "hailuo-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@runapi.ai/hailuo-mcp"
      ],
      "env": {
        "RUNAPI_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

hailuo-mcp connects MCP-compatible assistants to Hailuo models through RunAPI for image-to-video and text-to-video generation. It can submit asynchronous tasks, optionally wait for terminal results, retrieve task status, and return output URLs. A separate pricing tool works without authentication, while task creation and polling use RunAPI credentials. Reach for it when an agent should work with Hailuo specifically rather than the full RunAPI model catalog.

Use cases

  • Generate videos from text prompts with Hailuo
  • Animate source images through Hailuo image-to-video models
  • Check pricing before submitting a generation task
  • Poll asynchronous video tasks and collect output URLs

Key features

  • Hailuo image-to-video task creation
  • Hailuo text-to-video task creation
  • Optional waiting for terminal task status
  • Task status and payload retrieval
  • Model and endpoint pricing lookup
  • RunAPI API-key and login-based authentication

Tools4

What Hailuo MCP lets your agent do. Expand a tool for its parameters.

Self-reported~104 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

8/8 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · @runapi.ai/hailuo-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads819Package downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Tools exposed4Callable tools this server registers over MCP.

How Hailuo MCP works

What hailuo-mcp does

hailuo-mcp exposes the Hailuo model line on RunAPI through a focused MCP interface. It covers two video-generation workflows: converting an image into video and generating video from text. Both operations return a task identifier and status, with output URLs available when results are ready.

The server supports six model variants across the two endpoints. Image-to-video accepts hailuo-02-image-to-video-pro, hailuo-02-image-to-video-standard, hailuo-2.3-image-to-video-pro, and hailuo-2.3-image-to-video-standard. Text-to-video accepts hailuo-02-text-to-video-pro and hailuo-02-text-to-video-standard. This narrower scope suits assistants that should stay within Hailuo instead of discovering every model offered by RunAPI.

How it works

The server runs as an MCP process over standard input and output. An MCP host starts the package with npx, then makes its tools available to an assistant. Video-generation requests are asynchronous: the assistant can submit a task and wait for a terminal state, or return immediately with the task ID by setting wait to false.

Use get_task later to retrieve the current state and most recent payload for an existing task. The result tools can provide generated output URLs once processing is complete. check_pricing looks up pricing for a selected Hailuo model and endpoint before a task is created, and does not require sign-in.

Setup and configuration

Install the package through an MCP host using the stdio command npx -y @runapi.ai/hailuo-mcp. Claude Code can register it with claude mcp add hailuo -s user -- npx -y @runapi.ai/hailuo-mcp; project scope is also available when a repository should share the configuration. Other MCP hosts can use npx as the command with -y and @runapi.ai/hailuo-mcp as its argument.

Authentication is resolved in this order: the RUNAPI_API_KEY environment variable, the RunAPI configuration file at ~/.config/runapi/config.json, or no key. The environment variable is suitable for headless and CI environments. Interactive login stores credentials in that configuration file, which is also used by runapi login. A pre-provisioned configuration can contain an apiKey property. Credentials should not be committed to source control.

Tools and capabilities

  • image_to_video: submits a Hailuo image-to-video task, optionally waits for completion, and returns the task ID, status, and output URLs.
  • text_to_video: submits a Hailuo text-to-video task with the same optional waiting behavior and result fields.
  • get_task: checks an existing task and returns its current status and latest payload.
  • check_pricing: retrieves pricing for a Hailuo model and endpoint without authentication.

The assistant can combine these tools to inspect pricing first, create a task, and then report its identifier and generated URLs. It can also submit without waiting and check the task later.

Limitations and notes

The server is limited to Hailuo models and the two supported generation endpoints. Model availability may change between releases, so pricing lookup or the Hailuo model page should be used for the current catalog. Task creation and status retrieval require RunAPI authentication; pricing lookup does not. The package is licensed under Apache-2.0.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Hailuo MCP

hailuo-mcp is an MCP server that connects AI assistants to Hailuo models on RunAPI. Its main tools create image-to-video and text-to-video tasks, retrieve task status and payloads, and check model endpoint pricing. It supports asynchronous workflows with optional waiting for terminal results.

Install hailuo-mcp by configuring your MCP host to run `npx -y @runapi.ai/hailuo-mcp`. Claude Code can use `claude mcp add hailuo -s user -- npx -y @runapi.ai/hailuo-mcp`; other hosts can use the same stdio command.

Yes, hailuo-mcp works with Cursor through its standard MCP stdio configuration. Set the command to `npx` and pass `-y` and `@runapi.ai/hailuo-mcp` as arguments.

Set `RUNAPI_API_KEY` before starting the MCP host. The server checks that environment variable before the saved RunAPI configuration, making it suitable for headless and CI environments.

Yes, `check_pricing` works without authentication. Task creation and status polling still require RunAPI credentials supplied through `RUNAPI_API_KEY` or the saved configuration.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewHailuo MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/hailuo-mcp?style=directory)](https://allmcps.com/mcp/hailuo-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/hailuo-mcp"><img src="https://allmcps.com/api/badge/hailuo-mcp?style=directory" alt="Hailuo MCP on AllMCPs" /></a>