AI agents use image_multi_reference to create or update resources in Micu Image MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Micu Image MCP environment.
Based on the server description mentioning 'multi-reference image fusion' and the tool name, this likely generates or creates a new image by fusing multiple reference images. This is a Write operation (creating new data). Confidence is lowered due to the empty description.
From the tool's definition Tool name 'image_multi_reference' on a server described as supporting 'multi-reference image fusion'; description is empty/uninformative.
Documented attack patterns abuse exactly the kind of access image_multi_reference gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Micu Image MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for image_multi_reference:
{
"version": "1",
"default": "deny",
"tools": {
"image_multi_reference": {
"limits": [
{
"counter": "image_multi_reference_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}image_multi_reference 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.
Free to start. No card required.
image_multi_reference. It is categorised as a Write tool in the Micu Image MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Micu Image MCP server in PolicyLayer and add a rule for image_multi_reference: 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 Micu Image MCP. Nothing to install.
image_multi_reference is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the image_multi_reference 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_multi_reference. 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_multi_reference is provided by the Micu Image MCP server (subaru486desuwa/micu-image-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Micu Image MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Micu Image MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.