💡 Recommended: MiniMax CLI (mmx-cli) — our official command-line tool with the latest models and additional features including text, vision, search, and music cover. Works as an AI agent skill for Claude Code, Cursor, OpenClaw, etc.
MiniMax-MCP-JS - Official JavaScript implementation of MiniMax MCP
Related MCP server: MiniMax MCP
Get your API key from MiniMax.
Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.
Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.
Region | Global | Mainland |
MINIMAX_API_KEY | go get from MiniMax Global | go get from MiniMax |
MINIMAX_API_HOST |
Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:
{
"mcpServers": {
"MiniMax": {
"command": "uvx",
"args": [
"minimax-mcp",
"-y"
],
"env": {
"MINIMAX_API_KEY": "insert-your-api-key-here",
"MINIMAX_MCP_BASE_PATH": "local-output-dir-path, such as /User/xxx/Desktop",
"MINIMAX_API_HOST": "api host, https://api.minimax.io | https://api.minimaxi.com",
"MINIMAX_API_RESOURCE_MODE": "optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format"
}
}
}
}
⚠️ Warning: The API key needs to match the host. If an error "API Error: invalid api key" occurs, please check your api host:
Global Host：https://api.minimax.io
Mainland Host：https://api.minimaxi.com
If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu in the top left and select "Enable Developer Mode".
Go to Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server to add above config.
That's it. Your MCP client can now interact with MiniMax through these tools:
We support two transport types: stdio and sse.
stdio | SSE |
Run locally | Can be deployed locally or in the cloud |
Communication through | Communication through |
Input: Supports processing | Input: When deployed in the cloud, it is recommended to use |
tool | description |
| Convert text to audio with a given voice |
| List all voices available |
| Clone a voice using provided audio files |
| Generate a video from a prompt |
| Generate a image from a prompt |
| Query the result of video generation task |
| Generate a music track from a prompt and lyrics |
| Generate a voice from a prompt using preview text |
Voice Design: New voice_design tool - create custom voices from descriptive prompts with preview audio
Video Enhancement: Added MiniMax-Hailuo-02 model with ultra-clear quality and duration/resolution controls
Music Generation: Enhanced music_generation tool powered by music-1.5 model
voice_design - Generate personalized voices from text descriptions
generate_video - Now supports MiniMax-Hailuo-02 with 6s/10s duration and 768P/1080P resolution options
music_generation - High-quality music creation with music-1.5 model
Please ensure your API key and API host are regionally aligned
Region | Global | Mainland |
MINIMAX_API_KEY | go get from MiniMax Global | go get from MiniMax |
MINIMAX_API_HOST |
Please confirm its absolute path by running this command in your terminal:
which uvxOnce you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx").
generate_video in async-modeDefine completion rules before starting: Alternatively, these rules can be configured in your IDE settings (e.g., Cursor):
⚠️ Warning: Using these tools may incur costs.
Generate a video from a prompt.
COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.
Args:
model (str, optional): The model to use. Values range ["T2V-01", "T2V-01-Director", "I2V-01", "I2V-01-Director", "I2V-01-live"]. "Director" supports inserting instructions for camera movement control. "I2V" for image to video. "T2V" for text to video.
prompt (str): The prompt to generate the video from. When use Director model, the prompt supports 15 Camera Movement Instructions (Enumerated Values)
-Truck: [Truck left], [Truck right]
-Pan: [Pan left], [Pan right]
-Push: [Push in], [Pull out]
-Pedestal: [Pedestal up], [Pedestal down]
-Tilt: [Tilt up], [Tilt down]
-Zoom: [Zoom in], [Zoom out]
-Shake: [Shake]
-Follow: [Tracking shot]
-Static: [Static shot]
first_frame_image (str): The first frame image. The model must be "I2V" Series.
output_directory (str, optional): The directory to save the video to.
Returns:
Text content with the path to the output video file.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | T2V-01 | |
| prompt | No | ||
| output_directory | No | ||
| first_frame_image | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses API call cost and model-specific behavior (camera instructions), but lacks info on rate limits, auth, or what gets destroyed. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with cost warning upfront and parameter details indented. Slightly lengthy but every part is useful; could be more concise but not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description explains return value (path). All 4 parameters are described, and behavior for different models is covered. Complete for this tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, description fully explains all parameters: model values meaning, prompt camera instructions, first_frame_image for I2V, and output_directory. Adds substantial value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Generate a video from a prompt' with a specific verb and resource. It distinguishes from sibling tools (list_voices, play_audio, etc.) which handle audio or images, making video generation unique.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Includes a cost warning explicitly stating to use only when requested, plus details on when to choose Director vs I2V models. Provides clear context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all voices available. Only supports when api_host is https://api.minimax.chat
Args:
voice_type (str, optional): The type of voices to list. Values range ["all", "system", "voice_cloning"], with "all" being the default.
Returns:
Text content with the list of voices.
| Name | Required | Description | Default |
|---|---|---|---|
| voice_type | No | all |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool returns text content with the list of voices and mentions the api_host constraint. Basic behavioral info is present, but details on potential side effects, rate limits, or error handling are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, front-loads the main purpose, and uses a clear Args/Returns structure. Every sentence adds value, though it could be slightly more streamlined.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional parameter, no nested objects, no output schema), the description adequately covers the purpose, condition, parameter, and return type. It lacks notes on pagination or error cases but is sufficient for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no description for the voice_type parameter (0% coverage), but the description explicitly lists possible values (all, system, voice_cloning) and the default. This adds significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all voices available', providing a specific verb and resource. The unique constraint about api_host adds clarity, but it does not explicitly differentiate from sibling tools like text_to_audio or voice_clone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes an important usage condition (api_host must be https://api.minimax.chat) and details the optional voice_type parameter. However, it does not offer guidance on when to use this tool versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Play an audio file. Supports WAV and MP3 formats. Not supports video.
Args:
input_file_path (str): The path to the audio file to play.
is_url (bool, optional): Whether the audio file is a URL.
Returns:
Text content with the path to the audio file.
| Name | Required | Description | Default |
|---|---|---|---|
| is_url | No | ||
| input_file_path | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It covers supported formats and lack of video support, but does not explain how URLs are handled, error scenarios (e.g., file not found), permissions, or return value details beyond 'Text content with the path'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single informative sentence followed by structured Args and Returns sections. No redundant information, though it could be slightly more organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is too brief. It lacks details on prerequisites, error handling, behavior with URLs vs local files, and differentiation from sibling tools like text_to_audio or voice_clone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description partially compensates by listing parameters and stating that is_url is optional with default false. It adds context about supported formats (WAV/MP3) for input_file_path, but does not describe acceptable URL or path formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Play an audio file' and specifies supported formats (WAV, MP3). It also notes 'Not supports video', distinguishing it from sibling tools like generate_video. The verb and resource are clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for playing audio files but does not explicitly guide on when to use this tool versus alternatives like text_to_audio (for generation) or generate_video (for video). The 'Not supports video' hint is indirect.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Convert text to audio with a given voice and save the output audio file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop. Voice id is optional, if not provided, the default voice will be used.
COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.
Args:
text (str): The text to convert to speech.
voice_id (str, optional): The id of the voice to use. For example, "male-qn-qingse"/"audiobook_female_1"/"cute_boy"/"Charming_Lady"...
model (string, optional): The model to use.
speed (float, optional): Speed of the generated audio. Controls the speed of the generated speech. Values range from 0.5 to 2.0, with 1.0 being the default speed.
vol (float, optional): Volume of the generated audio. Controls the volume of the generated speech. Values range from 0 to 10, with 1 being the default volume.
pitch (int, optional): Pitch of the generated audio. Controls the speed of the generated speech. Values range from -12 to 12, with 0 being the default speed.
emotion (str, optional): Emotion of the generated audio. Controls the emotion of the generated speech. Values range ["happy", "sad", "angry", "fearful", "disgusted", "surprised", "neutral"], with "happy" being the default emotion.
sample_rate (int, optional): Sample rate of the generated audio. Controls the sample rate of the generated speech. Values range [8000,16000,22050,24000,32000,44100] with 32000 being the default sample rate.
bitrate (int, optional): Bitrate of the generated audio. Controls the bitrate of the generated speech. Values range [32000,64000,128000,256000] with 128000 being the default bitrate.
channel (int, optional): Channel of the generated audio. Controls the channel of the generated speech. Values range [1, 2] with 1 being the default channel.
format (str, optional): Format of the generated audio. Controls the format of the generated speech. Values range ["pcm", "mp3","flac"] with "mp3" being the default format.
language_boost (str, optional): Language boost of the generated audio. Controls the language boost of the generated speech. Values range ['Chinese', 'Chinese,Yue', 'English', 'Arabic', 'Russian', 'Spanish', 'French', 'Portuguese', 'German', 'Turkish', 'Dutch', 'Ukrainian', 'Vietnamese', 'Indonesian', 'Japanese', 'Italian', 'Korean', 'Thai', 'Polish', 'Romanian', 'Greek', 'Czech', 'Finnish', 'Hindi', 'auto'] with "auto" being the default language boost.
Returns:
Text content with the path to the output file and name of the voice used.
| Name | Required | Description | Default |
|---|---|---|---|
| vol | No | ||
| text | Yes | ||
| model | No | speech-02-hd | |
| pitch | No | ||
| speed | No | ||
| format | No | mp3 | |
| bitrate | No | ||
| channel | No | ||
| emotion | No | happy | |
| voice_id | No | female-shaonv | |
| sample_rate | No | ||
| language_boost | No | auto | |
| output_directory | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It mentions the output file creation and return value, but lacks details on overwrite behavior, error handling, or auth requirements. The cost warning adds some transparency, but overall the description is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured, starting with a clear summary, then a cost warning, then a detailed parameter list. It is front-loaded and organized, though slightly verbose in parameter explanations. Still, it earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (13 parameters, no output schema), the description covers purpose, cost, parameter meanings, and return type. It is fairly complete, though it could mention file naming conventions or directory creation behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description's Args section provides extensive meaning for all 13 parameters, including ranges, examples, and defaults (e.g., 'speed: 0.5 to 2.0, default 1.0'). This fully compensates for the missing schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Convert text to audio with a given voice and save the output audio file to a given directory,' using a specific verb ('convert') and resource ('text to audio'). It distinguishes from sibling tools like text_to_image and generate_video, as it focuses solely on audio generation from text.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a cost warning advising to only use when explicitly requested, providing explicit usage context. However, it does not differentiate from sibling tools like voice_clone or list_voices, which could be relevant when selecting a voice or cloning.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a image from a prompt.
COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.
Args:
model (str, optional): The model to use. Values range ["image-01"], with "image-01" being the default.
prompt (str): The prompt to generate the image from.
aspect_ratio (str, optional): The aspect ratio of the image. Values range ["1:1", "16:9","4:3", "3:2", "2:3", "3:4", "9:16", "21:9"], with "1:1" being the default.
n (int, optional): The number of images to generate. Values range [1, 9], with 1 being the default.
prompt_optimizer (bool, optional): Whether to optimize the prompt. Values range [True, False], with True being the default.
output_directory (str, optional): The directory to save the image to.
Returns:
Text content with the path to the output image file.
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | ||
| model | No | image-01 | |
| prompt | No | ||
| aspect_ratio | No | 1:1 | |
| output_directory | No | ||
| prompt_optimizer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry full behavioral disclosure. It mentions API call to Minimax and cost, but lacks details on side effects, authorization, rate limits, or error handling. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear purpose, cost warning, and parameter details. It is somewhat verbose but remains efficient, with front-loaded key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 parameters, no output schema, no annotations), the description covers all parameters, explains return value, and provides cost context. Missing error handling and edge cases, but reasonably complete for the task.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description lists all 6 parameters with explanations, including defaults and allowed values (e.g., aspect_ratio options). Since schema description coverage is 0%, this provides essential meaning beyond the schema, though some details like prompt_optimizer effect are minimal.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Generate a image from a prompt', using a specific verb and resource. It distinguishes from sibling tools like generate_video and text_to_audio, leaving no ambiguity about its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a cost warning advising to only use when explicitly requested, providing clear context for usage. However, it does not explicitly state when not to use or compare to alternatives, missing full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Clone a voice using provided audio files. The new voice will be charged upon first use.
COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.
Args:
voice_id (str): The id of the voice to use.
file (str): The path to the audio file to clone or a URL to the audio file.
text (str, optional): The text to use for the demo audio.
is_url (bool, optional): Whether the file is a URL. Defaults to False.
Returns:
Text content with the voice id of the cloned voice.
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | ||
| text | Yes | ||
| is_url | No | ||
| voice_id | Yes | ||
| output_directory | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavior. It mentions cost and charging but fails to clarify the role of 'voice_id' (input or output?) and does not explain side effects, prerequisites, or error handling. The ambiguous description of voice_id undermines transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is somewhat lengthy due to a docstring-style parameter list that partly duplicates the schema. The cost warning is helpful but adds extra length. The core purpose is front-loaded, but the structure could be tighter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 5 parameters and no output schema, the description should cover all aspects. It explains return format partly but misses output_directory, prerequisites for audio files, error handling, and the exact meaning of voice_id. This leaves significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description compensates by explaining file, text, and is_url. However, voice_id is poorly described as 'the id of the voice to use' without clarifying if it's source or target, and output_directory is omitted entirely.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Clone a voice using provided audio files', clearly identifying the verb (clone) and resource (voice). It distinguishes from siblings like text_to_audio and text_to_image by focusing on voice cloning from audio.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The cost warning advises to use only when explicitly requested, giving clear when-to-use guidance. However, it does not explicitly mention alternative tools like text_to_audio for simpler cases, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0generate_videolist_voicesplay_audiotext_to_audiotext_to_imagevoice_cloneEach tool has a clearly distinct purpose: video generation, voice listing, audio playback, text-to-audio, text-to-image, and voice cloning. No overlapping functionality.
Most tools follow verb_noun pattern (generate_video, list_voices, play_audio, voice_clone). Two tools use a conversion-style naming (text_to_audio, text_to_image) which is consistent with each other but slightly deviates from the main pattern.
6 tools is well-scoped for a multimedia generation server, covering video, audio, image, and voice features without being overwhelming or too sparse.
The tool set covers core creation operations (video, audio, image generation, voice cloning) but lacks management tools like listing, updating, or deleting generated content, which are notable gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for MiniMax H3 multimodal video generation
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
MCP server for Hailuo (MiniMax) AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MiniMax-AI/MiniMax-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
