AI agents call export_mermaid to retrieve information from AI Charts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads the current chart structure and converts/exports it to Mermaid syntax. It retrieves and transforms existing data without modifying, deleting, or executing anything. Similar to a 'get' or 'fetch' operation, it has no side effects on the underlying data.
From the tool's definition Export chart as Mermaid flowchart syntax
Attacks that exploit this kind of access
Export chart as Mermaid flowchart syntax. It is categorised as a Read tool in the AI Charts MCP Server, which means it retrieves data without modifying state.
Register the AI Charts MCP server in PolicyLayer and add a rule for export_mermaid: 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 AI Charts. Nothing to install.
export_mermaid 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 export_mermaid 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_mermaid. 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_mermaid is provided by the AI Charts MCP server (tjameswilliams/ai-charts). 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 →