Search for a municipality, district, neighbourhood, or postal code by name.
AI agents call search_boundaries to retrieve information from SB OGC MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Dutch mobility/geographic data to locate boundaries by name. It has no side effects—it merely returns matching geographic entities without modifying, executing external operations, or committing financial transactions. The blast radius of misuse is minimal; an AI agent could at worst retrieve information about many geographic areas, which poses no security risk.
From the tool's definition Tool performs a search/query operation to retrieve municipality, district, neighbourhood, or postal code information by name.
Attacks that exploit this kind of access
Search for a municipality, district, neighbourhood, or postal code by name. It is categorised as a Read tool in the SB OGC MCP MCP Server, which means it retrieves data without modifying state.
Register the SB OGC MCP server in PolicyLayer and add a rule for search_boundaries: 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 SB OGC MCP. Nothing to install.
search_boundaries 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_boundaries 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_boundaries. 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_boundaries is provided by the SB OGC MCP server (studio-bereikbaar/sb-ogc-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 →