使用 Mermaid 代码直接生成图表。
AI agents invoke generate_diagram to trigger actions in StarUML 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.
The tool takes Mermaid code as input and executes it to generate a diagram via StarUML. This constitutes executing code/triggering external operations whose effects depend on the provided arguments. It is not purely a read or write operation — it runs Mermaid code through the StarUML application.
From the tool's definition '直接生成图表' (directly generate diagrams) using Mermaid code, implying execution of diagram-generation logic from provided code input
Attacks that exploit this kind of access
使用 Mermaid 代码直接生成图表。. It is categorised as a Execute tool in the StarUML MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
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 Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 (stonesho/staruml_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →