AI agents call get_supported_options to retrieve information from Mermaid MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns metadata about supported conversion parameters (themes, formats). It performs no data modification, deletion, code execution, or external operations—only information lookup. The Chinese description confirms it is a getter/read operation. Severity is low because misuse cannot alter data or execute arbitrary operations.
From the tool's definition Tool name 'get_supported_options' and description 'get supported options for the converter, such as diagram themes and output formats' indicate querying/listing available configuration options with no side effects.
Documented attack patterns abuse exactly the kind of access get_supported_options gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mermaid MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_supported_options:
{
"version": "1",
"default": "deny",
"tools": {
"get_supported_options": {}
}
}get_supported_options 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.
获取转换器支持的选项，如图表主题和输出格式。. It is categorised as a Read tool in the Mermaid MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mermaid MCP Server MCP server in PolicyLayer and add a rule for get_supported_options: 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 Mermaid MCP Server. Nothing to install.
get_supported_options 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 get_supported_options 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 get_supported_options. 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.
get_supported_options is provided by the Mermaid MCP Server MCP server (wwwzhouhui/mermaid_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mermaid 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.
3 Mermaid MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.