AI agents call water.gauge 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.
water.gauge queries a public data source (USGS NWIS) and returns read-only hydrological observations. There are no side effects, data modifications, code execution, deletion, or financial transactions. The blast radius of misuse is minimal—an agent could only spam requests or consume quota, not damage systems or data.
From the tool's definition Tool retrieves real-time data ('Returns latest streamflow, gage height, water temp + site name/location') from a public USGS monitoring source with no modification capability implied. No write, execute, destructive, or financial operations are described.
Attacks that exploit this kind of access
Real-time US river/stream conditions from a USGS monitoring site. Pass site (USGS site number, e.g. 01646500). Returns latest streamflow, gage height, water temp + site name/location. Source: USGS NWIS (keyless). 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 water.gauge: 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.
water.gauge 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 water.gauge 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 water.gauge. 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.
water.gauge 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 →