What can you do with this server?

This MCP server exposes MiniMax speech, video, image, music, and file APIs as callable tools over stdio or streamable HTTP. * Speech: Create synchronous text-to-speech audio, create/poll async long-text T2A tasks, and clone voices from uploaded files. * Video: Generate videos from text prompts, input images, or templates, then poll task status for results. * Images: Generate images from text prompts and transform reference images with optional prompts. * Music: Generate music/vocal tracks or instrumentals, including cover-model workflows. * Files: Upload files, list/filter uploads, retrieve metadata or content, and delete files; uploads can support voice cloning and other downstream uses.

How do I use minimax-mcp-api?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@minimax-mcp-api Generate an image of a dog playing in the park." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

minimax-mcp-api

by ianrey258

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

minimax-mcp-api

A Model Context Protocol (MCP) server written in NestJS that wraps the MiniMax platform APIs and exposes them as MCP tools over stdio (local) or streamable HTTP (remote). The transport is picked at startup with MCP_TRANSPORT.

Prerequisites

Node.js ≥ 22 (per engines.node in package.json). Older versions lack the TypeScript target support used in tsconfig.build.json.

Related MCP server: minimax-llm-mcp

Install

npm install

Build

npm run build

Run (stdio)

node dist/main.js

Run (HTTP)

MCP_TRANSPORT=http MCP_AUTH_TOKEN=change-me PORT=3000 node dist/main.js
# or: npm run start:http   (with MCP_AUTH_TOKEN set in .env)

Serves streamable HTTP at POST /mcp. Every request must send Authorization: Bearer <MCP_AUTH_TOKEN>; anything else gets 401.

Environment variables

Variable	Required	Default	Description
`MINIMAX_API_KEY`	Yes	—	Bearer token for the MiniMax API
`MINIMAX_API_URL`	No	`https://api.minimax.io`	Base URL for the MiniMax API
`LOG_LEVEL`	No	`log`	One of `debug \| log \| warn \| error`
`NODE_ENV`	No	`development`	One of `development \| production \| test`
`MCP_TRANSPORT`	No	`stdio`	`stdio` or `http`
`PORT`	No	`3000`	HTTP listen port (`http` only)
`MCP_AUTH_TOKEN`	When `http`	—	Bearer token clients must send (`http` only)

Copy .env.example to .env and fill in MINIMAX_API_KEY before running.

MCP tools

Domain	Tool	Endpoint
Speech	`speech_t2a_http`	`POST /v1/t2a_v2`
Speech	`speech_t2a_async_create`	`POST /v1/t2a_async_v2`
Speech	`speech_t2a_async_query`	`GET /v1/query/t2a_async_query_v2`
Speech	`speech_voice_clone`	`POST /v1/voice_clone`
Video	`video_text_to_video`	`POST /v1/video_generation`
Video	`video_image_to_video`	`POST /v1/video_generation`
Video	`video_agent_create`	`POST /v1/video_generation`
Video	`video_agent_query`	`GET /v1/query/video_template_generation`
Image	`image_text_to_image`	`POST /v1/image_generation`
Image	`image_to_image`	`POST /v1/image_generation`
Music	`music_generate`	`POST /v1/music_generation`
File	`files_upload`	`POST /v1/files/upload`
File	`files_list`	`GET /v1/files/list`
File	`files_retrieve`	`GET /v1/files/retrieve`
File	`files_retrieve_content`	`GET /v1/files/retrieve_content`
File	`files_delete`	`DELETE /v1/files/delete`

(16 tools total over 5 domains.)

Configure Claude Desktop

Add to ~/.config/claude_desktop_config.json (note: the path to dist/main.js must be absolute):

{
  "mcpServers": {
    "minimax": {
      "command": "node",
      "args": ["/abs/path/to/minimax-mcp-api/dist/main.js"],
      "env": {
        "MINIMAX_API_KEY": "sk-..."
      }
    }
  }
}

Connect over HTTP (Claude Code)

claude mcp add --transport http minimax http://<host>:3000/mcp \
  --header "Authorization: Bearer <MCP_AUTH_TOKEN>"

Note: files_upload reads file_path from the server's filesystem, so over HTTP it can only upload files that exist on the host running the server.

Probe with MCP Inspector

npm run inspect

Troubleshooting

401/403 from any tool — MINIMAX_API_KEY is missing, malformed, or revoked. Verify with echo $MINIMAX_API_KEY and recopy the key from the MiniMax dashboard.
npm run build fails with TypeScript errors — Node version mismatch. Check node -v returns v22.x; older Node lacks the target support configured in tsconfig.build.json.
Claude Desktop can't connect — confirm args[0] is an absolute path to dist/main.js (not relative) and that the file exists (run npm run build first).
MINIMAX_API_URL change has no effect — stdio MCP servers read environment variables at startup only. Restart Claude Desktop (or the stdio process) after editing .env.

License

UNLICENSED — private project, not for redistribution.

Available Tools

16 tools

files_deleteB

Delete a file by file_id.

Inputs: file_id (required).

files_listB

List uploaded files, optionally filtered by purpose.

Inputs: after, limit, order, purpose.

files_retrieveA

Get metadata for a single file by file_id.

Inputs: file_id (required).

files_retrieve_contentA

Download a file. By default returns a summary (filename + bytes + content-type); pass as_hex=true to inline small file content as a hex string.

Inputs: file_id (required), as_hex.

files_uploadA

Upload a file (document, audio, image, etc.) for downstream use. Use purpose=voice_clone before speech_voice_clone.

Inputs: purpose (required), file_path (required), filename.

image_text_to_imageB

Generate images from a text prompt. Returns image URLs (typically valid 24h).

Inputs: model (required), prompt (required), n, seed, +6 more.

image_to_imageC

Transform a reference image guided by an optional prompt. Returns image URLs.

Inputs: model (required), image_url (required), n, seed, +5 more.

music_generateA

Generate music. Provide lyrics for vocal tracks; set is_instrumental=true for instrumental. music-cover* models require audio_url/audio_base64/cover_feature_id.

Inputs: model (required), lyrics, prompt, stream, +7 more.

speech_t2a_async_createA

Create an async long-text T2A task (up to 1M chars via text_file_id, or 50k via text). Returns a task_id to poll with speech_t2a_async_query.

Inputs: model (required), voice_id (required), vol, text, +13 more.

speech_t2a_async_queryA

Poll an async T2A task created by speech_t2a_async_create. Returns status (success|failed|expired|processing) and a file_id on success.

Inputs: task_id (required).

speech_t2a_httpA

Synchronous text-to-speech synthesis (≤10,000 chars). Returns audio URL + metadata. Use output_format="url" to receive a 24h-valid URL.

Inputs: text (required), model (required), voice_id (required), vol, +18 more.

speech_voice_cloneA

Clone a voice from an uploaded file_id (purpose=voice_clone). Cloned voices must be used within 168 hours or they are auto-deleted. Returns a demo_audio preview URL.

Inputs: file_id (required), voice_id (required), text, model, +6 more.

video_agent_createB

Create a video template/agent task. Returns a task_id to poll with video_agent_query.

Inputs: inputs (required), template_id (required), callback_url.

video_agent_queryA

Poll a video task. Returns status (Preparing|Processing|Success|Fail) and a video_url valid 9h on Success.

Inputs: task_id (required).

video_image_to_videoA

Generate a video from an input image (and optional prompt). Returns a task_id — poll with video_agent_query.

Inputs: model (required), image_url (required), prompt, duration, +3 more.

video_text_to_videoA

Generate a video from a text prompt. Returns a task_id — poll with video_agent_query.

Inputs: model (required), prompt (required), duration, resolution, +2 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

A3.6/5.0

Scored 2026-07-16 04:00 across 16 tools

Disambiguation5/5

Each tool targets a distinct function: file operations, image generation, music generation, speech synthesis (sync and async), voice cloning, and video generation. No two tools have overlapping purposes.

Naming Consistency4/5

Tools follow a consistent area_action pattern (e.g., files_delete, speech_t2a_async_create). Minor variations exist like 'image_to_image' versus 'image_text_to_image', and the use of 'agent' for video template tasks, but overall naming is predictable.

Tool Count4/5

16 tools cover a broad multi-modal domain without being excessive. Each tool serves a clear purpose, though some sub-areas (e.g., file management) have many tools while others have few.

Completeness4/5

File operations are complete (CRUD). Speech covers sync/async TTS and voice cloning. Video covers generation from text/image and agent tasks. Minor gaps like missing audio upload or image editing but domain scope is well-covered.

Maintenance

ActivityMaintained

ResponsivenessOutdated data

Resources

Related MCP Connectors

clipkitA
dev.clipkit
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Multimedia Processing Image & Video Processing
15219
https://www.clipkit.dev/mcp
mcp-minimax
io.github.AceDataCloud
MCP server for MiniMax H3 multimodal video generation
Image & Video Processing Multimedia Processing AI & Machine Learning
12
https://minimax.mcp.acedata.cloud/mcp
mcp-hailuo
io.github.AceDataCloud
MCP server for Hailuo (MiniMax) AI video generation
AI & Machine Learning Image & Video Processing
21
https://hailuo.mcp.acedata.cloud/mcp
strata
ai.klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Agent Orchestration Autonomous Agents Developer Tools
25,748
https://strata.klavis.ai/mcp/

Related MCP Servers

MiniMax Unified MCP
AI & Machine Learning Search Image & Video Processing
exomind-team
A
license
Not graded
quality
D
maintenance
Unifies MiniMax's multimodal generation, web search, image understanding, audio, video, and music tools into a single MCP server for use with Claude and other clients.
Updated 6 months ago (2026-05-20 12:07 UTC)
1
MIT
minimax-llm-mcp
AI & Machine Learning Developer Tools
webski101
A
license
A
quality
D
maintenance
Exposes the MiniMax M3 LLM API to MCP-compatible clients, enabling chat completions, text completions, tool calls, and token counting via stdio or SSE transport.
Updated 5 months ago (2026-06-12 09:57 UTC)
4
MIT
mmxomni
Image & Video Processing Audio Processing AI & Machine Learning
stlkrdumb
A
license
Not graded
quality
D
maintenance
Model Context Protocol server exposing MiniMax's image, speech, music, and video generation APIs as MCP tools for use with any MCP-aware host.
Updated 5 months ago (2026-06-14 08:33 UTC)
2,292 npm
MIT
gemini-mcp
AI & Machine Learning Image & Video Processing Multimedia Processing
chrischall
A
license
A
quality
A
maintenance
MCP server for Google Gemini media generation, exposing tools for generating and editing images, video, music, and async operations via stdio.
Updated 5 days ago (2026-11-08 19:34 UTC)
13
951 npm
MIT

minimax-mcp-api

Prerequisites

Install

Build

Run (stdio)

Run (HTTP)

Environment variables

MCP tools

Configure Claude Desktop

Connect over HTTP (Claude Code)

Probe with MCP Inspector

Troubleshooting

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MiniMax Unified MCP

minimax-llm-mcp

mmxomni

gemini-mcp