AI agents use generate_diagram to create or update resources in StarUML MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your StarUML MCP Server environment.
This tool creates new diagram objects in StarUML, which is reversible modification of project data. It does not execute code, delete data, or trigger financial operations. The severity is medium because an AI agent could generate numerous unwanted diagrams that clutter the project, but the operation is non-destructive and the diagrams can be deleted.
From the tool's definition Tool name and description indicate it 'Generate a diagram' which creates new data artifacts in StarUML. The sibling tools (get_all_diagrams_info, get_current_diagram_info, get_diagram_image_by_id) are Read operations, making this distinctly a Write operation…
Documented attack patterns abuse exactly the kind of access generate_diagram gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and StarUML MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_diagram:
{
"version": "1",
"default": "deny",
"tools": {
"generate_diagram": {
"limits": [
{
"counter": "generate_diagram_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_diagram 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.
Generate a diagram in StarUML. It is categorised as a Write tool in the StarUML MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the StarUML MCP Server MCP server in PolicyLayer and add a rule for generate_diagram: 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 StarUML MCP Server. Nothing to install.
generate_diagram 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 generate_diagram 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 generate_diagram. 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.
generate_diagram is provided by the StarUML MCP Server MCP server (staruml/staruml-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from StarUML 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 StarUML MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.