AI agents invoke image_composition to trigger actions in Jimeng MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external AI image composition operation via Jimeng AI, combining multiple images. It executes an external service call with side effects (API consumption, content generation). It is not purely a read operation, and while it creates content, the primary action is executing an external AI pipeline rather than writing to a simple data store.
From the tool's definition 合成/融合多张图像 (synthesize/fuse multiple images) — triggers an external AI generation operation
Documented attack patterns abuse exactly the kind of access image_composition gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jimeng MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for image_composition:
{
"version": "1",
"default": "deny",
"tools": {
"image_composition": {
"limits": [
{
"counter": "image_composition_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}image_composition stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
使用即梦4.5合成/融合多张图像。. It is categorised as a Execute tool in the Jimeng MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jimeng MCP Server MCP server in PolicyLayer and add a rule for image_composition: 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 Jimeng MCP Server. Nothing to install.
image_composition is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the image_composition 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 image_composition. 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.
image_composition is provided by the Jimeng MCP Server MCP server (wwwzhouhui/jimeng-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Jimeng MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Jimeng MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.