AI agents call get_diagram_feedback to retrieve information from Software Design Mermaid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool polls for user feedback on diagrams—a read operation that queries state without side effects. The polling mechanism is a retrieval pattern. No data is created, modified, deleted, or executed. Severity is low because feedback polling has no blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_diagram_feedback' and description 'Poll for user' indicate this retrieves feedback data without modifying or executing operations.
Documented attack patterns abuse exactly the kind of access get_diagram_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Software Design Mermaid, and nothing reaches the server without passing your rules. This is the rule we recommend for get_diagram_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"get_diagram_feedback": {}
}
}get_diagram_feedback 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.
Poll for user. It is categorised as a Read tool in the Software Design Mermaid MCP Server, which means it retrieves data without modifying state.
Register the Software Design Mermaid MCP server in PolicyLayer and add a rule for get_diagram_feedback: 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 Software Design Mermaid. Nothing to install.
get_diagram_feedback 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_diagram_feedback 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_diagram_feedback. 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_diagram_feedback is provided by the Software Design Mermaid MCP server (wzh4464/software-design-mermaid-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Software Design Mermaid, 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 Software Design Mermaid tools catalogued and risk-classified — across an index of 43,000+ MCP servers.