Skip to main content
mcpSource-backed
MiniMax logo

MiniMax MCP Server

Official MiniMax MCP server for using MiniMax text-to-speech, voice cloning, voice design, image generation, video generation, music generation, and media retrieval APIs from Claude and other MCP clients.

by MiniMax-AI · submitted by oktofeesh1·added 2026-06-06·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/MiniMax-AI/MiniMax-MCP/blob/main/README.md, https://github.com/MiniMax-AI/MiniMax-MCP
Brand
MiniMax
Brand domain
minimax.io
Brand asset source
brandfetch
Safety notes
Most generation tools call MiniMax APIs and can incur account costs; only enable them for users who are authorized to spend from the MiniMax account., Voice cloning and voice design can create synthetic voices; obtain consent and rights for any source audio or identity-like voice prompt before use., Image-to-video, voice cloning, audio playback, and local output modes can read local files or URLs and send media to MiniMax APIs., Generated image, audio, video, and music outputs should be reviewed for policy, copyright, likeness, brand, and release constraints before publication., The API key and API host must match the selected region or requests can fail with authentication errors.
Privacy notes
Prompts, preview text, lyrics, source audio, first-frame images, uploaded files, generated media requests, and task IDs may be sent to MiniMax APIs and included in MCP client or model logs., MINIMAX_API_KEY must stay in environment variables or secret managers and should never be committed to MCP config files., Local output mode can write generated files under the configured base path, and returned file paths may reveal workstation directory structure to the MCP client., URL resource mode returns generated media URLs that may need access controls, retention review, and sharing policy before being pasted into chats or tickets.
Author
MiniMax-AI
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

10 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.

0/5 ready
Account & credentials2Install & runtime1Review & approval1General110 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.

5 areas
  • SafetyPermissions & scopesMost generation tools call MiniMax APIs and can incur account costs; only enable them for users who are authorized to spend from the MiniMax account.
  • SafetyGeneralVoice cloning and voice design can create synthetic voices; obtain consent and rights for any source audio or identity-like voice prompt before use.
  • SafetyLocal filesImage-to-video, voice cloning, audio playback, and local output modes can read local files or URLs and send media to MiniMax APIs.
  • SafetyGeneralGenerated image, audio, video, and music outputs should be reviewed for policy, copyright, likeness, brand, and release constraints before publication.
  • SafetyCredentials & tokensThe API key and API host must match the selected region or requests can fail with authentication errors.
  • PrivacyNetwork accessPrompts, preview text, lyrics, source audio, first-frame images, uploaded files, generated media requests, and task IDs may be sent to MiniMax APIs and included in MCP client or model logs.
  • PrivacyCredentials & tokensMINIMAX_API_KEY must stay in environment variables or secret managers and should never be committed to MCP config files.
  • PrivacyLocal filesLocal output mode can write generated files under the configured base path, and returned file paths may reveal workstation directory structure to the MCP client.
  • PrivacyPermissions & scopesURL resource mode returns generated media URLs that may need access controls, retention review, and sharing policy before being pasted into chats or tickets.

Disclosure: Official MiniMax API tooling. MiniMax account usage, model access, regional hosts, quotas, and billing follow MiniMax's current platform terms.

Safety notes

  • Most generation tools call MiniMax APIs and can incur account costs; only enable them for users who are authorized to spend from the MiniMax account.
  • Voice cloning and voice design can create synthetic voices; obtain consent and rights for any source audio or identity-like voice prompt before use.
  • Image-to-video, voice cloning, audio playback, and local output modes can read local files or URLs and send media to MiniMax APIs.
  • Generated image, audio, video, and music outputs should be reviewed for policy, copyright, likeness, brand, and release constraints before publication.
  • The API key and API host must match the selected region or requests can fail with authentication errors.

Privacy notes

  • Prompts, preview text, lyrics, source audio, first-frame images, uploaded files, generated media requests, and task IDs may be sent to MiniMax APIs and included in MCP client or model logs.
  • MINIMAX_API_KEY must stay in environment variables or secret managers and should never be committed to MCP config files.
  • Local output mode can write generated files under the configured base path, and returned file paths may reveal workstation directory structure to the MCP client.
  • URL resource mode returns generated media URLs that may need access controls, retention review, and sharing policy before being pasted into chats or tickets.

Prerequisites

  • MiniMax API key from the correct regional MiniMax platform.
  • MINIMAX_API_HOST set to the matching Global or Mainland endpoint for the API key.
  • uv or uvx available to run the Python package.
  • Optional MINIMAX_MCP_BASE_PATH when using local output mode for generated media files.
  • Policy for paid API usage, voice cloning consent, copyrighted prompts or lyrics, and generated media review.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Tool listing metadata
Disclosure
Official MiniMax API tooling. MiniMax account usage, model access, regional hosts, quotas, and billing follow MiniMax's current platform terms.
Full copyable content
{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": ["minimax-mcp"],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_API_HOST": "https://api.minimax.io",
        "MINIMAX_API_RESOURCE_MODE": "url"
      }
    }
  }
}

About this resource

Content

MiniMax MCP Server is the official Python MCP server for MiniMax generation APIs. It lets Claude and other MCP clients call MiniMax tools for text-to-speech, voice listing, voice cloning, voice design, image generation, video generation, video-generation status checks, music generation, and audio playback.

Use it when a workflow needs agent-assisted media generation through a MiniMax account while keeping API keys and generated assets under explicit operational controls. It is especially useful for prototyping voice, image, video, and short music assets from Claude, Cursor, Windsurf, or other MCP-capable clients.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI package page, license, package manifest, server implementation, API client, utility helpers, constants, and package entrypoint for current installation and tool behavior.

Features

  • Convert text to speech with MiniMax voices.
  • List available system and voice-cloning voices.
  • Clone a voice from local audio files or audio URLs.
  • Design a voice from a prompt and preview text.
  • Generate images from prompts.
  • Generate videos from prompts or first-frame images, including async task handling.
  • Query video-generation task status.
  • Generate short music from prompts and lyrics.
  • Return generated media as URLs or save media locally depending on resource mode.

Installation

Configure the MCP server with a MiniMax API key and the matching regional API host:

{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": ["minimax-mcp"],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_API_HOST": "https://api.minimax.io",
        "MINIMAX_API_RESOURCE_MODE": "url"
      }
    }
  }
}

Use https://api.minimax.io for the Global host or the Mainland host documented in the upstream README when using a Mainland API key. Restart the MCP client after adding the server.

Use Cases

  • Ask Claude to draft and generate narration audio for a prototype.
  • Clone an approved voice sample for internal review workflows.
  • Generate concept images or short video clips from prompt iterations.
  • Query a pending MiniMax video-generation task from the MCP client.
  • Generate short music drafts from a prompt and lyrics.
  • Return media as URLs for review or save outputs under a controlled local base path.

Safety and Privacy

MiniMax MCP Server can spend API credits and send prompts, audio, images, video frames, lyrics, and generated-media requests to MiniMax services. Keep the MCP server disabled for users who are not authorized to use the account, and review outputs before publishing or sending to customers.

Voice cloning and voice design require special care. Use only audio and voice descriptions where consent, rights, and internal approval are clear, and avoid creating voice likenesses that could mislead listeners.

Keep the API key out of committed config files. If local output mode is enabled, review the base path and file-retention policy because generated media files and paths can reveal project context or workstation details.

Duplicate Check

No MiniMax MCP Server, MiniMax-AI/MiniMax-MCP, minimax-mcp, or matching MiniMax source URL was found in content/mcp.

Source citations

Add this badge to your README

Show that MiniMax MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/minimax-mcp-server.svg)](https://heyclau.de/entry/mcp/minimax-mcp-server)

How it compares

MiniMax MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

Official MiniMax MCP server for using MiniMax text-to-speech, voice cloning, voice design, image generation, video generation, music generation, and media retrieval APIs from Claude and other MCP clients.

Open dossier

Official ElevenLabs MCP server for generating speech, designing voices, cloning voices, transcribing audio, creating sound effects, and working with conversational audio agents through the ElevenLabs API.

Open dossier

Source-install MCP server for controlling a local ComfyUI instance so Claude can generate, view, regenerate, manage, and publish image, audio, and video assets through workflow-backed tools.

Open dossier

MCP server and CLI for AI image and video generation with gallery search, prompt enhancement, model listing, local preferences, ComfyUI workflows, MeiGen Cloud, and OpenAI-compatible provider support.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandMiniMax logoMiniMaxElevenLabs MCP Server logoElevenLabs MCP ServerMeiGen AI Design MCP logoMeiGen AI Design MCP
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorMiniMax-AIElevenLabsJoe NortonMeiGen
Added2026-06-062026-06-062026-06-062026-06-06
Platforms
Harness
Source repo
Safety notesMost generation tools call MiniMax APIs and can incur account costs; only enable them for users who are authorized to spend from the MiniMax account. Voice cloning and voice design can create synthetic voices; obtain consent and rights for any source audio or identity-like voice prompt before use. Image-to-video, voice cloning, audio playback, and local output modes can read local files or URLs and send media to MiniMax APIs. Generated image, audio, video, and music outputs should be reviewed for policy, copyright, likeness, brand, and release constraints before publication. The API key and API host must match the selected region or requests can fail with authentication errors.ElevenLabs MCP Server can call paid ElevenLabs API endpoints; text-to-speech, voice design, voice cloning, audio isolation, transcription, sound generation, music, and agent workflows can consume account credits. Voice cloning and voice conversion can create realistic synthetic speech, so require documented consent and review before processing a person's voice or publishing generated audio. Generated speech, sound effects, music, transcripts, and conversation-agent configuration can affect public-facing content; review prompts, voice IDs, output format, language, and destination before publishing or sending. File output mode writes generated files to disk under the configured base path; restrict that path to an approved directory and avoid broad home, desktop, or shared folders in production. Use separate API keys or workspaces for test and production clients, monitor credit usage, and disable tools in clients that should not spend credits. Some operations may take longer than normal MCP tool timeouts; do not retry expensive generation calls blindly.ComfyUI MCP Server can submit prompts and workflows to a local ComfyUI instance, create generated media, poll jobs, cancel jobs, and publish assets into project directories. Generated images, audio, and video can contain unsafe, infringing, biased, misleading, or policy-sensitive content depending on prompts, models, LoRAs, and workflows. Publishing tools can copy, compress, convert, overwrite, and update manifest entries for assets, so verify target filenames and directories before use. Custom workflows can expose arbitrary parameters and may run heavy GPU workloads or fail if nodes, models, or paths are missing. Keep the server bound to local trusted clients unless you have added appropriate authentication and network controls.MeiGen can submit image and video generation jobs to external providers or a local ComfyUI backend. Image and video generation may spend credits, use paid APIs, or consume local GPU resources depending on the configured provider. Local reference images can be compressed and uploaded through the configured upload gateway before being sent to API providers. Video generation can take minutes, may time out at the MCP client, and should not be retried blindly because jobs or credits may already be in progress. ComfyUI workflow import and modification can run local workflows; review workflow JSON and custom nodes before use.
Privacy notesPrompts, preview text, lyrics, source audio, first-frame images, uploaded files, generated media requests, and task IDs may be sent to MiniMax APIs and included in MCP client or model logs. MINIMAX_API_KEY must stay in environment variables or secret managers and should never be committed to MCP config files. Local output mode can write generated files under the configured base path, and returned file paths may reveal workstation directory structure to the MCP client. URL resource mode returns generated media URLs that may need access controls, retention review, and sharing policy before being pasted into chats or tickets.The MCP client can expose ElevenLabs API keys, voice IDs, text prompts, voice descriptions, uploaded audio samples, generated audio paths, transcripts, diarized speaker labels, and conversational-agent settings. Uploaded audio and generated outputs may contain biometric voice characteristics, names, background sounds, private conversations, or copyrighted material. File, resource, and both output modes can retain generated audio locally, in MCP resources, in logs, or in chat transcripts depending on the client. Treat voice samples and transcripts as sensitive data, and delete generated files or cached resources when they are no longer needed. Review ElevenLabs account, retention, residency, and enterprise data-residency settings before using the server with regulated or customer data.Prompts, negative prompts, generated media, workflow parameters, model names, job IDs, asset metadata, and publish paths can appear in MCP responses, logs, and model transcripts. Generated assets may be stored in ComfyUI output folders, the MCP asset registry, project publish directories, or manifests. Do not feed private images, brand assets, customer materials, or regulated media into workflows unless the local model environment is approved for that data. Review model and workflow licenses before publishing or redistributing generated assets.API tokens, OpenAI-compatible credentials, provider base URLs, upload gateway URLs, ComfyUI URLs, preferences, recent generations, prompts, model IDs, and output paths can reveal private creative workflows. Uploaded reference images may become public URLs through the configured upload gateway before generation. Prompts, reference images, generated image URLs, generated video URLs, saved outputs, and favorite prompts can contain client work, brand plans, product images, personal likenesses, or unreleased campaigns. Keep secrets in MCP client environment configuration, review generated media before sharing, and remove local outputs when retention is no longer needed.
Prerequisites
  • MiniMax API key from the correct regional MiniMax platform.
  • MINIMAX_API_HOST set to the matching Global or Mainland endpoint for the API key.
  • uv or uvx available to run the Python package.
  • Optional MINIMAX_MCP_BASE_PATH when using local output mode for generated media files.
  • Python 3.11 or newer with `uvx` available.
  • An ElevenLabs API key for the account and workspace you intend Claude to use.
  • Review of ElevenLabs pricing, credits, voice-cloning policy, content rules, and data handling before enabling tools that generate or process audio.
  • An approved output directory when using file-based generated audio output.
  • A local ComfyUI installation with required models and workflows.
  • Python and the repository requirements installed from the source checkout.
  • The MCP server launched from the cloned repository or with paths adjusted for your client.
  • Approved prompts, source assets, model licenses, and publish locations for generated media.
  • Node.js 18 or newer.
  • MCP client that can launch a local Node stdio server.
  • Optional MeiGen API token, OpenAI-compatible API key, or local ComfyUI workflow configuration for generation tools.
  • Provider pricing, credits, model limits, and content policy reviewed before image or video generation.
Install
uvx minimax-mcp
uvx elevenlabs-mcp
git clone https://github.com/joenorton/comfyui-mcp-server && cd comfyui-mcp-server && pip install -r requirements.txt
Run `npx -y meigen` from an MCP client, or use the upstream plugin/init commands after reviewing provider credentials and generated-media costs.
Config
{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": [
        "minimax-mcp"
      ],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_API_HOST": "https://api.minimax.io",
        "MINIMAX_API_RESOURCE_MODE": "url"
      },
      "type": "stdio"
    }
  }
}
Manual-only setup:
claude mcp add elevenlabs --env ELEVENLABS_API_KEY=YOUR_ELEVENLABS_API_KEY -- uvx elevenlabs-mcp
{
  "mcpServers": {
    "comfyui-mcp-server": {
      "command": "python",
      "args": ["server.py", "--stdio"],
      "env": {
        "COMFYUI_URL": "",
        "COMFY_MCP_WORKFLOW_DIR": "",
        "COMFYUI_OUTPUT_ROOT": "",
        "COMFY_MCP_ASSET_TTL_HOURS": "24"
      }
    }
  }
}
{
  "mcpServers": {
    "meigen": {
      "command": "npx",
      "args": ["-y", "meigen"],
      "env": {
        "MEIGEN_API_TOKEN": "{meigen-api-token}"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.