AI agents call find_schools_nearby to retrieve information from OpenStreetMap MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves nearby schools based on location. It queries read-only geospatial data (OpenStreetMap) to return points of interest, with no capability to create, modify, or delete data. The misuse risk is minimal—an agent could at worst retrieve unnecessary school location data or make irrelevant queries. No side effects, data modification, code execution, or financial impact are possible.
From the tool's definition Tool name 'find_schools_nearby' and sibling tools like 'find_nearby_places', 'find_parking_facilities', and 'find_ev_charging_stations' all follow a consistent query/retrieval pattern.
Documented attack patterns abuse exactly the kind of access find_schools_nearby gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenStreetMap MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find_schools_nearby:
{
"version": "1",
"default": "deny",
"tools": {
"find_schools_nearby": {}
}
}find_schools_nearby 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.
find_schools_nearby. It is categorised as a Read tool in the OpenStreetMap MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenStreetMap MCP Server MCP server in PolicyLayer and add a rule for find_schools_nearby: 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 OpenStreetMap MCP Server. Nothing to install.
find_schools_nearby 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 find_schools_nearby 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 find_schools_nearby. 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.
find_schools_nearby is provided by the OpenStreetMap MCP Server MCP server (jagan-shanmugam/open-streetmap-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenStreetMap MCP 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.
12 OpenStreetMap MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.