Export diagram to various formats (returns instructions for rendering).
AI agents use export_diagram to create or update resources in DiagramMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DiagramMCP environment.
The export_diagram tool creates output files in various formats (SVG, PNG, etc.) from diagram definitions. This is a Write operation as it generates new data artifacts, albeit reversibly.
From the tool's definition Tool name 'export_diagram' and description 'Export diagram to various formats (returns instructions for rendering)' indicate diagram file creation/modification operations.
Attacks that exploit this kind of access
Export diagram to various formats (returns instructions for rendering). It is categorised as a Write tool in the DiagramMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Diagram MCP server in PolicyLayer and add a rule for export_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 DiagramMCP. Nothing to install.
export_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 export_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 export_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.
export_diagram is provided by the Diagram MCP server (lelondelonmelon/diagrammcp). 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 →