Search for cities in the local CSV files from the static directory. Useful for finding French cities and their details. Examples: - Find all cities containing
AI agents call search_local_cities to retrieve information from MCP Weather Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from local CSV files to return city information. It has no side effects—it neither modifies data, executes code, deletes records, nor commits financial transactions. It is a simple read operation that falls squarely into the 'Read' category with low severity due to limited blast radius if misused by an AI agent.
From the tool's definition Tool description states 'Search for cities in the local CSV files from the static directory' and explicitly mentions finding city details. The action is purely informational retrieval with no modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access search_local_cities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Weather Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_local_cities:
{
"version": "1",
"default": "deny",
"tools": {
"search_local_cities": {}
}
}search_local_cities is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for cities in the local CSV files from the static directory. Useful for finding French cities and their details. Examples: - Find all cities containing. It is categorised as a Read tool in the MCP Weather Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Weather Server MCP server in PolicyLayer and add a rule for search_local_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 MCP Weather Server. Nothing to install.
search_local_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 search_local_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 search_local_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.
search_local_cities is provided by the MCP Weather Server MCP server (tjarriault/mcp-weather-sample). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Weather Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Weather Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.