AI agents call poi.near 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.
This tool queries OpenStreetMap data to retrieve geographic and business information about nearby points of interest. It is purely informational with no side effects, data modification, code execution, or financial impact. The output is read-only data retrieval sorted by proximity.
From the tool's definition Tool description states it 'Find points of interest near a coordinate' and 'Returns name, OSM id, lat/lon, distance in meters, address, phone, website, hours, brand, cuisine.' These are all retrieval and query operations with no modification, deletion, or…
Attacks that exploit this kind of access
Find points of interest near a coordinate. Backed by OpenStreetMap (Overpass API). Returns name, OSM id, lat/lon, distance in meters, address, phone, website, hours, brand, cuisine. Nearest-first. 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 poi.near: 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.
poi.near 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 poi.near 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 poi.near. 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.
poi.near 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 →