Compare a metric across cities.
AI agents call compare_cities to retrieve information from VayuChat MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and compares metrics from an existing dataset without creating, modifying, deleting, or executing arbitrary code. While the server as a whole includes Execute tools like 'execute_code', this specific tool appears limited to querying and comparing data across different city records.
From the tool's definition The tool 'compare_cities' is described as comparing 'a metric across cities.' This is a data retrieval and comparison operation with no modification, deletion, or code execution capabilities.
Attacks that exploit this kind of access
Compare a metric across cities. It is categorised as a Read tool in the VayuChat MCP MCP Server, which means it retrieves data without modifying state.
Register the VayuChat MCP server in PolicyLayer and add a rule for compare_cities: 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 VayuChat MCP. Nothing to install.
compare_cities 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 compare_cities 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 compare_cities. 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.
compare_cities is provided by the VayuChat MCP server (nipunbatra/vayuchat-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 →