Return enabled engines and supported models/knobs for current credentials.
AI agents call get_model_capabilities to retrieve information from Image Gen MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns metadata about available image generation models and their parameters. It has no side effects—it merely reads and reports system capabilities. This is a classic Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_model_capabilities' and description 'Return enabled engines and supported models/knobs for current credentials' indicate a query operation that retrieves configuration and capability information without modifying, executing, or deleting…
Documented attack patterns abuse exactly the kind of access get_model_capabilities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Image Gen MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_model_capabilities:
{
"version": "1",
"default": "deny",
"tools": {
"get_model_capabilities": {}
}
}get_model_capabilities 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.
Return enabled engines and supported models/knobs for current credentials. It is categorised as a Read tool in the Image Gen MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Image Gen MCP Server MCP server in PolicyLayer and add a rule for get_model_capabilities: 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 Image Gen MCP Server. Nothing to install.
get_model_capabilities 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 get_model_capabilities 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 get_model_capabilities. 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.
get_model_capabilities is provided by the Image Gen MCP Server MCP server (simonchoi034/image-gen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Image Gen 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.
3 Image Gen MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.