Get paginated list of reference points from USGS Real-Time Flood Impacts API
AI agents call get_reference_points to retrieve information from USGS Water MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public water monitoring reference point data from a USGS API without modifying, deleting, or executing operations. It is a straightforward data query with no side effects. The low severity reflects that misuse would only expose publicly available water monitoring information with no destructive or operational impact.
From the tool's definition Tool description explicitly states 'Get paginated list of reference points' - a retrieval operation with no modification capabilities.
Attacks that exploit this kind of access
Get paginated list of reference points from USGS Real-Time Flood Impacts API. It is categorised as a Read tool in the USGS Water MCP MCP Server, which means it retrieves data without modifying state.
Register the USGS Water MCP server in PolicyLayer and add a rule for get_reference_points: 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 USGS Water MCP. Nothing to install.
get_reference_points 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 get_reference_points 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 get_reference_points. 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.
get_reference_points is provided by the USGS Water MCP server (pgiffy/usgs-water-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 →