# MiniMax-AI/MiniMax-MCP

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Repository: https://github.com/MiniMax-AI/MiniMax-MCP
Canonical: https://ross.abutalabs.com/products/minimax-mcp
Homepage: https://www.minimax.io/platform
Language: Python
License: MIT
License Family: permissive
Topics: image-generation, mcp, mcp-server, mcp-tools, text-to-speech, video-generation, image-to-video, text-to-image, text-to-video, voice-cloning
Last push: 2026-08-20T12:06:49+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 36
- inputs: {"age_days": 510, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1569, forks 279 (observed 2026-08-28T04:05:05.220124+00:00)

## What it is
The official MiniMax Model Context Protocol (MCP) server, written in Python, exposing MiniMax's text-to-speech, image generation, and video generation APIs as MCP tools. It lets MCP-compatible clients like Claude or Cursor generate speech, images, and videos directly from chat.

## Use cases
- generate speech audio from text inside an MCP client
- create images from text prompts via Claude or Cursor
- generate videos from text or image prompts
- clone a voice and use it for TTS
- convert an image into a video
- integrate MiniMax media generation APIs into AI agent workflows

## When to choose
- you use an MCP-compatible client and want MiniMax TTS, image, or video generation as tools
- you want an official, maintained wrapper around MiniMax media APIs
- you want voice cloning or image-to-video exposed to AI agents

## When to avoid
- you need direct programmatic API access without MCP
- you don't have a MiniMax API key or paid plan
- you need other providers' media generation models

## Facets
- artifact type: service
- maturity: active
- function: mcp, tts, image-processing, video-processing, sdk
- domain: artificial-intelligence, large-language-models, developer-tools, media
- platform: python, cross-platform, cli
- tags: mcp-server, text-to-speech, text-to-image, text-to-video, image-to-video, voice-cloning, minimax-api, ai-tools

## Member repositories
- MiniMax-AI/MiniMax-MCP (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.220124+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:58:35.044549+00:00, confidence not recorded.
  - readme: https://github.com/MiniMax-AI/MiniMax-MCP (fetched 2026-08-28T04:05:05.220124+00:00, sha 4e7e7378376a)
  - homepage: https://www.minimax.io/platform (fetched 2026-08-29T11:28:46.532144+00:00, sha 1955dd402f0f)
  - site_page: https://platform.minimax.io/docs/api-reference/video-generation-v2-create (fetched 2026-08-29T11:28:46.542813+00:00, sha 75d5cfe870c0)
  - site_page: https://platform.minimax.io/docs (fetched 2026-08-29T11:28:46.546398+00:00, sha 1955dd402f0f)
  - site_page: https://platform.minimax.io/docs/pricing/overview (fetched 2026-08-29T11:28:46.548044+00:00, sha 80efb607b836)
  - site_page: https://platform.minimax.io/docs/api-reference/api-overview (fetched 2026-08-29T11:28:46.549547+00:00, sha adf42f4d8db4)
  - site_page: https://platform.minimax.io/docs/token-plan/intro (fetched 2026-08-29T11:28:46.551238+00:00, sha 024fa6c387ba)
  - site_page: https://platform.minimax.io/docs/release-notes/models (fetched 2026-08-29T11:28:46.552822+00:00, sha 594ca6f3f8bf)
  - site_page: https://minimax.io (fetched 2026-08-29T11:28:46.544628+00:00, sha da282795b4a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.