Skip to main content
Glama

MiniMax MCP Server by useapi.net (third-party)

Run the MiniMax agent

minimax_run_agent

Give the hailuoai.video AI agent a task in plain words ("generate a 16:9 video of…", "generate an image…", "generate a song based on my lyrics") and the models it may use; it picks among them and returns the files it made. Optional reference files by public URL. Uses the account's MiniMax credits. Runs as a job: waits up to ~50 s, then returns the jobId for minimax_get_agent_job. For direct control use minimax_create_video / minimax_create_image. POST /agent.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>",
      "models": "<models>"
    },
    "name": "minimax_run_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
modelsYesThe models the agent may use, e.g. ["hailuo-2.3", "nano-banana-2"]. Video: hailuo-2.3, hailuo-2.3-fast, hailuo-02, veo-3.1, veo-3.1-fast, veo-3.1-s2v, veo-3.1-s2v-fast. Image: nano-banana-2, nano-banana, seedream, kontext, qwen, kolors, midjourney-v7, midjourney-niji7, seedream-5.0. Audio: speech-2.5-hd-preview, speech-2.5-turbo-preview, minimax-music-2.0.
promptYesThe task. Say what to make (video, image, song, speech), and the aspect ratio or resolution if it matters.
accountNoThe account id from minimax_list_accounts. Optional when you have one account, required with more.
fileUrlsNoUp to 3 public https URLs of reference files (images to edit or animate, for example), each up to 20 MB; downloaded here and attached to the request.
replyRefNoOptional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters.
replyUrlNoOptional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), it discloses that generation consumes the account's MiniMax credits, that the call blocks for up to ~50 s before falling back to a jobId, and that reference files are downloaded server-side. It does not say what happens to credits on failure or whether a retry re-bills, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and example phrasing, then job behavior, then alternatives — a sensible order. The three inline example prompts add concreteness but lengthen the opening sentence slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, no-output-schema, credit-consuming async job tool, the description covers what it produces (generated files), the blocking-vs-jobId lifecycle, the follow-up tool, the cost source, and the direct-control alternatives. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a real semantic point for 'models' — the list is a permitted set the agent chooses among, not a single fixed model — and restates the public-URL constraint for reference files. The remaining parameters (wait, account, replyRef, replyUrl) are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a concrete verb and resource — give the hailuoai.video agent a plain-language task plus allowed models, and it returns the generated files. It explicitly separates this from minimax_create_video and minimax_create_image, so an agent can tell which tool to pick without reading the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names the condition that selects this tool (natural-language, model-agnostic task where the agent picks the model) and names the alternatives for direct control (minimax_create_video / minimax_create_image). It also states the async job path: after ~50 s the jobId is returned for minimax_get_agent_job.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources