Mcp Minimax

io.github.AceDataCloudPublished by GitHub account AceDataCloudv2026.11.1.0Updated Nov 1, 2026

MCP server for MiniMax H3 multimodal video generation

VerifiedStreamable HTTPWeb executableMedia & DesignAI & ML

Overview

AI-generated overview

MiniMax H3 video generation server that lets an assistant create videos from text, images or audio and manage the resulting tasks.

What you can do
  • Generate videos from a text prompt, from one to nine image URLs, or from audio plus reference images, or from the full content schema
  • List available models and workflows to see supported input modes and constraints
  • List generation tasks with optional timestamp filters
  • Retrieve one task or several tasks in a batch to check status and get resulting video URLs
  • Delete a generation task
When to use it
Useful when you want an assistant to produce short MiniMax H3 videos (4–15 seconds, 768P or 2K, various aspect ratios) from prompts, images or audio, and to poll or clean up the asynchronous tasks afterwards.
Requirements
Either the hosted endpoint with OAuth sign-in to an AceDataCloud account, or an AceDataCloud API token passed as ACEDATACLOUD_API_TOKEN (local stdio via uvx or pip, or an Authorization Bearer header for the hosted endpoint). Local runs still call the AceDataCloud API, so network access is needed.
Before you install
Generation is metered and may consume account balance; review current pricing before real operations. The API token is a secret: keep it in a credential store or environment variable, not in prompts, shared configs or commits, and do not configure both OAuth and a fixed Authorization header. Deleting a task is destructive, and submitted tasks may fail or be rejected by content moderation.

Installation

In SourceWeft

  1. Open Mcp Minimax in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.AceDataCloud%2Fmcp-minimax/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "minimax": {
      "type": "http",
      "url": "https://minimax.mcp.acedata.cloud/mcp"
    }
  }
}

README

MiniMax H3 MCP

[PyPI] [Python] [License]

Model Context Protocol server for MiniMax H3 multimodal video generation through AceDataCloud.

Capabilities

  • Text-to-video
  • Image-, video-, and audio-guided video generation
  • 4–15 second output in 768P or 2K, with adaptive, landscape, portrait, and square ratios
  • Optional asynchronous submission, task retrieval, batch retrieval, and deletion
  • Hosted OAuth HTTP transport and local stdio transport

Tools

ToolPurpose
minimax_generate_video_from_textGenerate from a detailed prompt
minimax_generate_video_from_imagesGenerate from one to nine image URLs
minimax_generate_video_from_audioGenerate with one to three audio URLs and required images
minimax_generate_videoGenerate from the full documented content schema
minimax_list_tasksList tasks with optional timestamp filters
minimax_get_taskRetrieve one task
minimax_get_tasks_batchRetrieve several tasks
minimax_delete_taskDelete one task
minimax_list_modelsShow model constraints
minimax_list_actionsShow available workflows

Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is https://minimax.mcp.acedata.cloud/mcp. Choose one route for the MCP client:

RouteWhen to use itCredential setup
Hosted OAuthThe client supports remote MCP OAuthAdd only the URL, then sign in to AceDataCloud and approve access. No token needs to be pasted into client configuration.
Hosted API tokenThe client cannot finish OAuth, or you need an explicit integration credentialSend an AceDataCloud API token in the Authorization: Bearer … header. Keep it in a local secret store or environment variable.
Local stdioThe client runs a local MCP processInstall mcp-minimax and pass ACEDATACLOUD_API_TOKEN to that process. It still calls the AceDataCloud API.

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). DCR registers the client application; it is not an API key. OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review current service documentation and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed Authorization header for the same server.

Hosted OAuth examples

  • Claude and Claude Desktop chat: Add a remote custom connector in Customize → Connectors → Add custom connector, enter https://minimax.mcp.acedata.cloud/mcp, select sign-in, and choose Register automatically if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local claude_desktop_config.json is a separate setup. Claude connector guide.
  • Claude Code: claude mcp add --transport http --scope user minimax https://minimax.mcp.acedata.cloud/mcp, then claude mcp login minimax. Check /mcp. Claude Code MCP guide.
  • Cursor: Add a remote server with only https://minimax.mcp.acedata.cloud/mcp. For a project, merge the entry below into <project>/.cursor/mcp.json; for personal use, use ~/.cursor/mcp.json. Cursor MCP guide.
  • VS Code / Copilot: Run MCP: Add Server, select HTTP, enter https://minimax.mcp.acedata.cloud/mcp, then finish the browser sign-in. New portable workspace configs use <project>/.mcp.json; the VS Code-specific format below uses <project>/.vscode/mcp.json or the user profile. Check MCP: List Servers. VS Code MCP setup.
  • Codex: codex mcp add minimax --url https://minimax.mcp.acedata.cloud/mcp, then codex mcp login minimax. Its user settings are in ~/.codex/config.toml. Official Codex MCP guide.

Cursor project config (OAuth):

json
{  "mcpServers": {    "minimax": {"url": "https://minimax.mcp.acedata.cloud/mcp"}  }}

VS Code-specific workspace config (OAuth):

json
{  "servers": {    "minimax": {"type": "http", "url": "https://minimax.mcp.acedata.cloud/mcp"}  }}

Hosted API token

  1. Open Ace Data Cloud → Applications. Sign in, or register an account first.
  2. Find General application. If it has not been created, choose Initialize General Application. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and current pricing.
  3. Copy the API Key from the application card, or open Keys / Manage Keys → Create to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.
  4. When creating a key, review Expiration Time, Set Usage Limitation, and Allowed APIs. Enable only the restrictions you need, allow the operations you will call, then click Create and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.
  5. Copy only the token value, without quotation marks, spaces, or Bearer . An API Key / API Token field expects this raw value; only a manually configured HTTP Authorization header needs the Bearer prefix. A platform-... account-management token cannot replace a generation API key.

[Copy an application API key or open Manage Keys]

[Create a separately named key with optional restrictions]

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

bash
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'claude mcp add --transport http --scope user minimax https://minimax.mcp.acedata.cloud/mcp \  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"

For a Claude Code project config, put a variable reference in <project>/.mcp.json and set that variable in the environment that launches Claude Code:

json
{  "mcpServers": {    "minimax": {      "type": "http",      "url": "https://minimax.mcp.acedata.cloud/mcp",      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}    }  }}

Cursor uses a different environment-variable syntax in ~/.cursor/mcp.json or an uncommitted project config:

json
{  "mcpServers": {    "minimax": {      "url": "https://minimax.mcp.acedata.cloud/mcp",      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}    }  }}

In VS Code, run MCP: Open User Configuration and merge this server plus its masked input; ${input:...} is for VS Code's user/workspace format and is not portable to the Agent Host .mcp.json format:

json
{  "inputs": [    {"id": "acedata-minimax-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}  ],  "servers": {    "minimax": {      "type": "http",      "url": "https://minimax.mcp.acedata.cloud/mcp",      "headers": {"Authorization": "Bearer ${input:acedata-minimax-token}"}    }  }}

For Cline, use its MCP configuration UI or CLI file ~/.cline/data/settings/cline_mcp_settings.json; its remote transport value is streamableHttp. For JetBrains AI Assistant, add a remote URL from Settings → Tools → AI Assistant → Model Context Protocol (MCP). For Zed, use a context_servers entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. Cline · JetBrains · Zed.

Local stdio

Install the package and give the local process an API token:

bash
python -m pip install mcp-minimaxexport ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'mcp-minimax

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (~/Library/Application Support/Claude/claude_desktop_config.json on macOS). uvx requires uv on PATH:

json
{  "mcpServers": {    "minimax": {      "command": "uvx",      "args": ["mcp-minimax"],      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}    }  }}

Keep this user-level file private. Self-hosted HTTP uses mcp-minimax --transport http --port 8000; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

Check before using the service

  1. https://minimax.mcp.acedata.cloud/health returning {"status":"ok"} checks endpoint reachability only.
  2. Confirm that the MCP client loads tools. minimax_list_models is a reference tool; it does not verify downstream API access or balance.
  3. If you need a full API check, call minimax_generate_video with your own valid input after reviewing current service documentation and displayed pricing. If the result contains a task ID, call minimax_get_task on that same ID until terminal success or failure. Do not resubmit the operation just to check progress.

For 401, check which auth route the client used and whether the token or OAuth session is valid. A 403 may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

Development

bash
pip install -e ".[dev,test]"ruff check .pytest --cov=core --cov=toolsmypy core tools

Documentation

Documentation

License

MIT

Source: README.md at commit 9f00b88

Tools

10

minimax_list_models

Describe the MiniMax H3 model and supported input modes.

Takes no parameters.

minimax_list_actions

List MiniMax H3 generation and task tools.

Takes no parameters.

minimax_list_tasks

List video generation tasks, optionally filtered by creation timestamp.

Parameterslimitoffsetcreated_at_maxcreated_at_min

minimax_get_task

Query the status and result of a video generation task. Use this to check if a generation is complete and retrieve the resulting video URLs and other metadata. Use this when: - You want to check if a generation has completed - You need to retrieve video URLs from a previous generation - You want to get the full details of a generated video Task states: - 'queued' or 'running': Generation is still in progress - 'succeeded': Generation finished successfully - 'failed' or 'cancelled': Generation reached a terminal error state Returns: Task status and generated video information including URLs and status.

Parameterstask_idrequired

minimax_get_tasks_batch

Query multiple video generation tasks at once. Efficiently check the status of multiple tasks in a single request. More efficient than calling minimax_get_task multiple times. Use this when: - You have multiple pending generations to check - You want to get status of several videos at once - You're tracking a batch of generations Returns: Status and video information for all queried tasks.

Parameterstask_idsrequired

minimax_delete_task

Delete a MiniMax video generation task.

Parameterstask_idrequired

minimax_generate_video_from_text

Generate a MiniMax H3 video from a text prompt.

Parametersasyncmodelratiopromptrequireddurationresolutioncallback_url

minimax_generate_video_from_images

Generate from one first-frame image or multiple reference images. Single image uses first_frame mode; multiple images use reference_image mode. The two modes are mutually exclusive per MiniMax H3 v2 API contract.

Parametersasyncmodelratiopromptrequireddurationimage_urlsrequiredresolutioncallback_url

minimax_generate_video_from_audio

Generate a MiniMax H3 video guided by audio and reference images. Audio-guided generation uses reference mode exclusively (reference_audio forces the entire content into reference-to-video mode per the H3 v2 contract).

Parametersasyncmodelratiopromptrequireddurationaudio_urlsrequiredimage_urlsrequiredresolutioncallback_url

minimax_generate_video

Generate a video from the full MiniMax content schema.

Parametersasyncmodelratiocontentrequireddurationresolutioncallback_url

Version history

13
  1. v2026.11.1.0LatestNov 1, 2026
  2. v2026.10.18.4Oct 18, 2026
  3. v2026.10.18.0Oct 18, 2026
  4. v2026.10.12.1Oct 12, 2026
  5. v2026.10.8.0Oct 8, 2026
  6. v2026.10.7.0Oct 7, 2026
  7. v2026.10.6.0Oct 6, 2026
  8. v2026.10.5.0Oct 5, 2026
  9. v2026.10.4.1Oct 4, 2026
  10. v2026.10.4.0Oct 4, 2026
  11. v2026.9.30.0Sep 30, 2026
  12. v2026.9.29.0Sep 29, 2026
  13. v2026.8.28.0Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts