list_icons
AI agents call list_icons to retrieve information from Azure Diagram MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate a static set of icons available in the diagram DSL, with no capability to modify, delete, or execute operations. Even if used maliciously, listing icons poses minimal security risk. Confidence is slightly reduced due to the empty description, but the name provides sufficient evidence for classification.
From the tool's definition Tool name 'list_icons' indicates a retrieval operation that lists available icons, likely for use in diagram generation. No description provided, but naming convention strongly suggests a query/enumeration function with no side effects.
Attacks that exploit this kind of access
list_icons. It is categorised as a Read tool in the Azure Diagram MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure Diagram MCP Server MCP server in PolicyLayer and add a rule for list_icons: 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 Azure Diagram MCP Server. Nothing to install.
list_icons 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 list_icons 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 list_icons. 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.
list_icons is provided by the Azure Diagram MCP Server MCP server (jah-yee/diagrams-mcp-server). 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 →