search_category
AI agents call search_category to retrieve information from OSM MCP Analytics Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the OSM analytics context and the pattern of sibling tools, 'search_category' most likely searches or filters geospatial features by category. No modification, deletion, code execution, or financial impact is suggested. Confidence is moderate (0.75) because the description is empty and category intent must be inferred from context.
From the tool's definition Tool name 'search_category' suggests querying or filtering data by category. The description is empty, but sibling tools on this server (find_nearby_places, find_ev_charging_stations, find_parking_facilities, find_schools_nearby, explore_area) are all…
Attacks that exploit this kind of access
search_category. It is categorised as a Read tool in the OSM MCP Analytics Server MCP Server, which means it retrieves data without modifying state.
Register the OSM MCP Analytics Server MCP server in PolicyLayer and add a rule for search_category: 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 OSM MCP Analytics Server. Nothing to install.
search_category 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_category 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_category. 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_category is provided by the OSM MCP Analytics Server MCP server (neco001/openstreetmap-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 →