AI agents call describe_image to retrieve information from Midjourney MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes image data to produce textual output. It does not create, modify, delete, execute code, or trigger external operations. It is a straightforward descriptive analysis function analogous to searching or fetching information, placing it squarely in the Read category with low severity since misuse would only return undesired but non-damaging text output.
From the tool's definition The tool description states it generates 'text descriptions of an image' — a pure retrieval/analysis operation with no side effects, modifications, or external state changes.
Documented attack patterns abuse exactly the kind of access describe_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Midjourney MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_image:
{
"version": "1",
"default": "deny",
"tools": {
"describe_image": {}
}
}describe_image is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate text descriptions of an image. It is categorised as a Read tool in the Midjourney MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Midjourney MCP Server MCP server in PolicyLayer and add a rule for describe_image: 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 Midjourney MCP Server. Nothing to install.
describe_image is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the describe_image 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.
Set action: deny in the PolicyLayer policy for describe_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.
describe_image is provided by the Midjourney MCP Server MCP server (z23cc/midjourney-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Midjourney MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Midjourney MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.