You MUST use this tool whenever you need to analyze, describe, or extract information from an image. An LLM-powered vision tool that can analyze and interpret image content from local files or URLs based on your instructions. Only JPEG, PNG, and WebP formats are supported. Args: prompt (str...
Part of the Minimax Coding Plan MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call understand_image to perform operations in Minimax Coding Plan. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.
Applying a policy to understand_image gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.
Apply a rate limit to control usage and monitor for unexpected behaviour.
tools:
understand_image:
rules:
- action: allow
rate_limit:
max: 60
window: 60 See the full Minimax Coding Plan policy for all 2 tools.
Agents calling other-class tools like understand_image have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Other risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
You MUST use this tool whenever you need to analyze, describe, or extract information from an image. An LLM-powered vision tool that can analyze and interpret image content from local files or URLs based on your instructions. Only JPEG, PNG, and WebP formats are supported. Args: prompt (str): A text prompt describing what you want to analyze or extract from the image. image_source (str): The location of the image to analyze. - HTTP/HTTPS URL: "https://example.com/image.jpg" - Local file path (relative or absolute) - If path starts with @, strip the @ prefix before passing. It is categorised as a Other tool in the Minimax Coding Plan MCP Server, which means it performs auxiliary operations.
Add a rule in your Intercept YAML policy under the tools section for understand_image. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Minimax Coding Plan MCP server.
understand_image is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the understand_image rule in your Intercept 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.
Set action: deny in the Intercept policy for understand_image. 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.
understand_image is provided by the Minimax Coding Plan MCP server (minimax-coding-plan-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.