Current US State Department travel advisories. Omit country for the full list, or pass a country name (case-insensitive substring) for one. Returns the advisory level (1 Normal Precautions → 4 Do Not Travel) with label, a plain-text summary of reasons, the official link, and published date. Live ...
AI agents call travel.advisory to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and presents read-only information from a public government data source. There are no creation, modification, deletion, execution, or financial operations. The data returned is informational only and impacts no system state. Low severity because misuse would only affect user perception of travel information.
From the tool's definition Tool description states it returns current US State Department travel advisories from the official travel.state.gov RSS feed.
Attacks that exploit this kind of access
Current US State Department travel advisories. Omit country for the full list, or pass a country name (case-insensitive substring) for one. Returns the advisory level (1 Normal Precautions → 4 Do Not Travel) with label, a plain-text summary of reasons, the official link, and published date. Live from the official travel.state.gov RSS feed (public domain). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for travel.advisory: 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 Mcp. Nothing to install.
travel.advisory 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 travel.advisory 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 travel.advisory. 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.
travel.advisory is provided by the MCP server (@2sio/mcp). 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 →