# How to integrate MiniMax MCP with Atomic Agent

```json
{
  "title": "How to integrate MiniMax MCP with Atomic Agent",
  "toolkit": "MiniMax",
  "toolkit_slug": "minimax",
  "framework": "Atomic Agent",
  "framework_slug": "atomic-agent",
  "url": "https://composio.dev/toolkits/minimax/framework/atomic-agent",
  "markdown_url": "https://composio.dev/toolkits/minimax/framework/atomic-agent.md",
  "updated_at": "2026-11-01T07:20:23.631Z"
}
```

## Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including MiniMax.
This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a MiniMax account. See the [Atomic Agent documentation](https://atomicagent.io/docs/?cta_placement=atomic-agent-docs) for installation instructions.

## Also integrate MiniMax with

- [ChatGPT](https://composio.dev/toolkits/minimax/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/minimax/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/minimax/framework/hermes-agent)

## TL;DR

### How Atomic Agent connects to MiniMax
Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.
Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

## Connect MiniMax to Atomic Agent

### Connect MiniMax to Atomic Agent
- Sign up or sign in to the [Composio dashboard](https://dashboard.composio.dev/?cta_placement=atomic-agent-api-key). Copy your API key.
- In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
- Ask Atomic Agent to do something in MiniMax. It searches Composio for the right tool.
- On first use, open the sign-in link returned in the chat. Connect your MiniMax account, then return to Atomic Agent to continue.
### Headless setup
Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

```bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY
```

## What is the MiniMax MCP server, and what's possible with it?

The MiniMax MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your MiniMax account. It provides structured and secure access to text generation, image creation, video generation, speech synthesis, audio transcription, voice tools, and file workflows, so your agent can generate content, create and track videos, synthesize and transcribe audio, manage voices, and upload or retrieve files on your behalf.
- Text and image creation: Have your agent generate text with MiniMax models, count or estimate input tokens, and create images from detailed prompts.
- Video generation and tracking: Direct your agent to create videos from text or reference media, use templates, enhance video prompts, check task progress, and retrieve finished results.
- Speech and audio workflows: Let the agent synthesize spoken audio, start and monitor long-form speech tasks, and transcribe uploaded audio with options for timestamps, speaker separation, subtitles, and language hints.
- Custom voice management: Instruct your agent to list available voices, design a voice from a description, clone a voice from an uploaded sample, create preview audio, or remove voices you no longer need.
- File and generated output management: Have your agent upload files for supported MiniMax workflows, review available files, retrieve file details, download generated content, or delete files.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `MINIMAX_CLONE_VOICE` | Clone Voice | Create a reusable MiniMax cloned voice from an uploaded voice sample, optionally generating paid preview audio. |
| `MINIMAX_COUNT_MESSAGE_TOKENS` | Count Message Tokens | Count input tokens for an Anthropic-compatible message payload without generating content. |
| `MINIMAX_CREATE_ASYNC_SPEECH` | Create Async Speech | Start a long-form asynchronous MiniMax speech synthesis task from inline text or one uploaded text file. |
| `MINIMAX_CREATE_LEGACY_VIDEO` | Create Legacy Video | Start a MiniMax v1 Hailuo text, image, first-and-last-frame, or subject-reference video task with mode-specific validation. |
| `MINIMAX_CREATE_RESPONSE` | Create OpenAI-Compatible Response | Call MiniMax through its OpenAI Responses compatibility contract and return one non-streaming response object. |
| `MINIMAX_CREATE_TEMPLATE_VIDEO` | Create Template Video | Start a MiniMax Video Agent task using an official template and its ordered text and media inputs. |
| `MINIMAX_CREATE_VIDEO` | Create Video | Start a MiniMax H3 video v2 generation task from text and optional reference media. Returns an asynchronous task ID for MINIMAX_GET_VIDEO_TASK. |
| `MINIMAX_CREATE_VIDEO_PROMPT` | Create Video Prompt | Start a MiniMax H3 Context-IR task that converts multimodal context into an enhanced video prompt. |
| `MINIMAX_DELETE_FILE` | Delete File | Permanently delete one MiniMax file by its exact ID and storage-purpose category. This operation cannot be undone. |
| `MINIMAX_DELETE_VIDEO_TASK` | Cancel or Delete Video Task | Cancel a queued MiniMax video v2 task, or permanently delete a completed or failed task record. The operation performed depends on the task's current state. |
| `MINIMAX_DELETE_VOICE` | Delete Voice | Permanently delete an eligible MiniMax cloned or designed voice. |
| `MINIMAX_DESIGN_VOICE` | Design Voice | Design a reusable MiniMax voice from a description and return its paid preview as a downloadable audio file. |
| `MINIMAX_DOWNLOAD_FILE` | Download File | Download the binary contents of one generated MiniMax file and return a managed file reference. Response headers determine the original name and MIME type when available; downloads larger than 100 MB are rejected. |
| `MINIMAX_ESTIMATE_RESPONSE_INPUT_TOKENS` | Estimate Responses Input Tokens | Estimate input tokens using MiniMax's OpenAI Responses compatibility contract without generating model output. |
| `MINIMAX_GENERATE_ANTHROPIC_MESSAGE` | Generate Anthropic-Compatible Message | Call MiniMax through its Anthropic Messages compatibility contract and return one non-streaming message response. |
| `MINIMAX_GENERATE_IMAGE` | Generate Image | Generate one or more images from a text prompt, optionally guided by a subject reference. |
| `MINIMAX_GENERATE_NATIVE_CHAT_COMPLETION` | Generate Native Chat Completion | Call MiniMax's native chatcompletion_v2 contract and return one non-streaming completion, including native sensitivity metadata. |
| `MINIMAX_GENERATE_TEXT` | Generate Text | Generate one non-streaming OpenAI-compatible chat completion, including optional reasoning and tool calls. |
| `MINIMAX_GET_ACCOUNT_BALANCE` | Get Account Balance | Get the connected global pay-as-you-go MiniMax account's available, cash, voucher, credit, owed, and balance-alert amounts. |
| `MINIMAX_GET_ANTHROPIC_MODEL` | Get Anthropic-Compatible Model | Retrieve one MiniMax text model through the Anthropic Models compatibility contract. |
| `MINIMAX_GET_ASYNC_SPEECH_TASK` | Get Async Speech Task | Get the status and generated file reference for a MiniMax asynchronous speech synthesis task. |
| `MINIMAX_GET_FILE` | Get File | Retrieve metadata for one MiniMax file by its exact ID, including a temporary download URL when MiniMax provides one for a generated output. |
| `MINIMAX_GET_LEGACY_VIDEO_TASK` | Get Legacy Video Task | Get the status and output file metadata of a MiniMax v1 legacy video task. |
| `MINIMAX_GET_TEMPLATE_VIDEO_TASK` | Get Template Video Task | Get the status and temporary result URL of a MiniMax Video Agent template task. |
| `MINIMAX_GET_TEXT_MODEL` | Get OpenAI-Compatible Text Model | Retrieve one MiniMax text model through the OpenAI Models compatibility contract. |
| `MINIMAX_GET_VIDEO_TASK` | Get Video Task | Get the current state and output of one MiniMax video v2 task created within the last seven days. Failed tasks are returned as task records with error details. |
| `MINIMAX_LIST_ANTHROPIC_MODELS` | List Anthropic-Compatible Models | List one page of MiniMax text models through the Anthropic Models compatibility contract, using its after_id or before_id cursors. |
| `MINIMAX_LIST_FILES` | List Files | List MiniMax files for one upload-purpose category. MiniMax documents no pagination for this endpoint. |
| `MINIMAX_LIST_TEXT_MODELS` | List Text Models | List text model IDs currently available to the connected MiniMax API key. |
| `MINIMAX_LIST_VIDEO_TASKS` | List Video Tasks | List one page of MiniMax video v2 tasks from the last seven days, optionally filtered by status, task ID, model, or task type. |
| `MINIMAX_LIST_VOICES` | List Voices | List system, cloned, generated, or all voices that can be used for speech synthesis. |
| `MINIMAX_REGENERATE_VIDEO` | Regenerate Video | Regenerate an eligible MiniMax-H3 768P source video as a 2K video, using either its task ID or the exact original inputs and source video. |
| `MINIMAX_SYNTHESIZE_SPEECH` | Synthesize Speech | Synchronously synthesize up to 9,999 characters of text and return the decoded audio as a downloadable file. |
| `MINIMAX_TRANSCRIBE_AUDIO` | Transcribe Audio | Transcribe an uploaded audio file with optional language hints, timestamps, speaker diarization, subtitle output, or assembled streaming output. |
| `MINIMAX_UPLOAD_FILE` | Upload File | Upload one file to MiniMax as multipart/form-data for voice cloning, async speech, video understanding, or video generation. |

## Supported Triggers

None listed.

## Troubleshooting

### Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

### Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

### Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See [Composio pricing](/pricing) for the current limits that apply to your connection.

## Complete Code

None listed.

## Conclusion

### Use MiniMax from Atomic Agent
With your account connected, ask Atomic Agent to work with MiniMax in natural language. You can connect more apps through the same Composio integration as you need them.
Visit the [Atomic Agent website](https://atomicagent.io/?cta_placement=atomic-agent-site) or inspect the [Atomic Agent source code](https://github.com/AtomicBot-ai/atomic-agent?cta_placement=atomic-agent-repo).

## How to build MiniMax MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/minimax/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/minimax/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/minimax/framework/hermes-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Black Forest Labs](https://composio.dev/toolkits/bfl) - Black Forest Labs provides hosted FLUX models for generating and editing images and videos. It offers fast, flexible media creation with asynchronous processing and fine-tuning support.
- [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [BotMape](https://composio.dev/toolkits/botmape) - BotMape is an API platform for building AI agents, knowledge bases, conversations, and messages. Use it to manage agent workflows and track usage analytics from one place.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and MiniMax MCP?

With a standalone MiniMax MCP server, the agents and LLMs can only access a fixed set of MiniMax tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from MiniMax and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Atomic Agent?

Yes, you can. Atomic Agent fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right MiniMax tools.

### Can I manage the permissions and scopes for MiniMax while using Tool Router?

Yes, absolutely. You can configure which MiniMax scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your MiniMax data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)