Generate an image using Replicate models: Flux 1.1 Pro (default), Qwen Image, or SeedDream-4. Requires REPLICATE_API_TOKEN.
AI agents invoke image.generate.replicate to trigger actions in ImageGen 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 API call to Replicate's image generation service, executing a remote operation whose effects depend on the arguments passed (model choice, prompt, etc.). It is not a simple read/query, nor does it write local data — it invokes an external compute service.
From the tool's definition Generate an image using Replicate models... Requires REPLICATE_API_TOKEN
Documented attack patterns abuse exactly the kind of access image.generate.replicate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ImageGen MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for image.generate.replicate:
{
"version": "1",
"default": "deny",
"tools": {
"image.generate.replicate": {
"limits": [
{
"counter": "image.generate.replicate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}image.generate.replicate 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.
Generate an image using Replicate models: Flux 1.1 Pro (default), Qwen Image, or SeedDream-4. Requires REPLICATE_API_TOKEN. It is categorised as a Execute tool in the ImageGen MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ImageGen MCP Server MCP server in PolicyLayer and add a rule for image.generate.replicate: 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 ImageGen MCP Server. Nothing to install.
image.generate.replicate 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.generate.replicate 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.generate.replicate. 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.generate.replicate is provided by the ImageGen MCP Server MCP server (writingmate/imagegen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ImageGen 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.
4 ImageGen MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.