Start multi-reference image generation in the background and return a job_id immediately.
AI agents invoke image_multi_reference_async to trigger actions in EFLOWCODE Image MCP. 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.
image_multi_reference_async triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Start multi-reference image generation in the background and return a job_id immediately. It is categorised as a Execute tool in the EFLOWCODE Image MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the EFLOWCODE Image MCP server in PolicyLayer and add a rule for image_multi_reference_async: 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 EFLOWCODE Image MCP. Nothing to install.
image_multi_reference_async 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_multi_reference_async 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_async. 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_async is provided by the EFLOWCODE Image MCP server (wenninghan/eflowcode-image-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.