List all supported Mermaid diagram types (22+ types including flowchart, sequence, class, etc.).
AI agents call listSupportedTypes to retrieve information from Mcp Mermiad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward informational query that retrieves metadata about the server's capabilities. It has no ability to modify data, execute code, delete resources, or cause financial impact. The blast radius of misuse is minimal—an agent could only receive a list of supported types, which is harmless publicly-available information.
From the tool's definition Tool name and description indicate it 'List all supported Mermaid diagram types' — a retrieval operation with no side effects. Returns information about supported diagram types without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access listSupportedTypes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Mermiad, and nothing reaches the server without passing your rules. This is the rule we recommend for listSupportedTypes:
{
"version": "1",
"default": "deny",
"tools": {
"listSupportedTypes": {}
}
}listSupportedTypes 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.
List all supported Mermaid diagram types (22+ types including flowchart, sequence, class, etc.). It is categorised as a Read tool in the Mcp Mermiad MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mermiad MCP server in PolicyLayer and add a rule for listSupportedTypes: 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 Mcp Mermiad. Nothing to install.
listSupportedTypes 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 listSupportedTypes 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 listSupportedTypes. 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.
listSupportedTypes is provided by the Mcp Mermiad MCP server (narasimhaponnada/mermaid-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Mermiad, 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.
9 Mcp Mermiad tools catalogued and risk-classified — across an index of 43,000+ MCP servers.