Fetch current water data from USGS for specified sites
AI agents call fetch_usgs_data 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 publicly available water monitoring data from USGS stations without any side effects. It performs a simple query operation to obtain real-time measurements. There is no evidence of write, delete, execution, or financial operations. The blast radius of misuse is minimal—an agent could at worst request excessive data or access information already public. This is a straightforward read operation.
From the tool's definition Tool description states 'Fetch current water data' and server description emphasizes 'fetch instantaneous measurements' and 'allows users to fetch' data.
Attacks that exploit this kind of access
Fetch current water data from USGS for specified sites. 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 fetch_usgs_data: 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.
fetch_usgs_data 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 fetch_usgs_data 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 fetch_usgs_data. 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.
fetch_usgs_data 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 →