Medium Risk

submit_image_generation

Generate images asynchronously. RECOMMENDED: Submit multiple tasks in batch to saturate rate limits, then call task_barrier once to wait for all completions. Returns task ID only - actual files available after task_barrier.

How to control submit_image_generation ↓

AI agents use submit_image_generation to create or update resources in Minimax MCP Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Minimax MCP Tools environment.

Medium Risk

This tool generates and writes image files to the filesystem via an external AI API. It creates new data (images) which is a Write operation. The blast radius is medium since it can consume API credits and write files, but does not delete data or move money directly.

From the tool's definition 'Generate images asynchronously' and 'Returns task ID only - actual files available after task_barrier' — creates image files as output

Documented attack patterns abuse exactly the kind of access submit_image_generation gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Minimax MCP Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for submit_image_generation:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "submit_image_generation": {
      "limits": [
        {
          "counter": "submit_image_generation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

submit_image_generation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Minimax MCP Tools — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the submit_image_generation tool do? +

Generate images asynchronously. RECOMMENDED: Submit multiple tasks in batch to saturate rate limits, then call task_barrier once to wait for all completions. Returns task ID only - actual files available after task_barrier. It is categorised as a Write tool in the Minimax MCP Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on submit_image_generation? +

Register the Minimax MCP Tools MCP server in PolicyLayer and add a rule for submit_image_generation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Minimax MCP Tools. Nothing to install.

What risk level is submit_image_generation? +

submit_image_generation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit submit_image_generation? +

Yes. Add a rate_limit block to the submit_image_generation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block submit_image_generation completely? +

Set action: deny in the PolicyLayer policy for submit_image_generation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides submit_image_generation? +

submit_image_generation is provided by the Minimax MCP Tools MCP server (psycharch/minimax-mcp-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Minimax MCP Tools tool call.

Deterministic rules across all 3 Minimax MCP Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 Minimax MCP Tools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.