AI agents call park.lookup 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 queries publicly available data from the US National Park Service without any side effects. It matches the Read category profile: search/filter/get operations with no impact on data or systems. Severity is low because misuse poses minimal risk—worst case is excessive API queries or information disclosure of public data.
From the tool's definition Tool is described as a 'Unified read API' that supports filtering and querying across park resources (parks, alerts, campgrounds, events, newsreleases, thingstodo, visitorcenters).
Attacks that exploit this kind of access
Unified read API over the US National Park Service developer.nps.gov. resource = parks | alerts | campgrounds | events | newsreleases | thingstodo | visitorcenters. Filter by parkCode (CSV), state, free-text query. 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 park.lookup: 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.
park.lookup 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 park.lookup 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 park.lookup. 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.
park.lookup 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 →