Render saved notes as a Prefab card grid.
AI agents call show_dashboard to retrieve information from EAG MCP Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and renders existing data (saved notes) for display purposes. There are no side effects, no data modifications, no code execution, and no destructive or financial operations. The action is purely presentational and informational, making it a clear Read category tool with low severity risk.
From the tool's definition Tool 'show_dashboard' with description 'Render saved notes as a Prefab card grid' performs a read operation that retrieves and displays already-saved notes without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Render saved notes as a Prefab card grid. It is categorised as a Read tool in the EAG MCP Demo MCP Server, which means it retrieves data without modifying state.
Register the EAG MCP Demo MCP server in PolicyLayer and add a rule for show_dashboard: 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 EAG MCP Demo. Nothing to install.
show_dashboard 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 show_dashboard 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 show_dashboard. 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.
show_dashboard is provided by the EAG MCP Demo MCP server (skinnymonk/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 →