AI agents call display-fact to retrieve information from Widget MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool displays a static fact (e.g., 'The capital of France is Paris'). It retrieves or presents read-only information with no side effects. The description is extremely minimal and uninformative, which lowers confidence, but in context of the server (displaying facts as widgets) it is clearly a read/display operation with negligible blast radius.
From the tool's definition Tool name 'display-fact' and description 'The capital of France' — appears to display a static informational fact
Documented attack patterns abuse exactly the kind of access display-fact gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Widget MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for display-fact:
{
"version": "1",
"default": "deny",
"tools": {
"display-fact": {}
}
}display-fact 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.
The capital of France. It is categorised as a Read tool in the Widget MCP MCP Server, which means it retrieves data without modifying state.
Register the Widget MCP server in PolicyLayer and add a rule for display-fact: 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 Widget MCP. Nothing to install.
display-fact 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 display-fact 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 display-fact. 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.
display-fact is provided by the Widget MCP server (ref-tools/widget-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Widget MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Widget MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.