get_asset_url
AI agents call get_asset_url to retrieve information from OpenLandMap 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 asset URLs from the OpenLandMap STAC catalog—a read-only operation with no side effects. Even if an agent misuses it, the worst outcome is accessing or exfiltrating publicly available environmental data.
From the tool's definition Tool name 'get_asset_url' and server context indicate retrieval of URLs to geospatial data assets. The OpenLandMap server provides access to 'discover, search, and retrieve Cloud-Optimized GeoTIFFs' without mentioning creation, modification, deletion, or…
Attacks that exploit this kind of access
get_asset_url. It is categorised as a Read tool in the OpenLandMap MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenLandMap MCP Server MCP server in PolicyLayer and add a rule for get_asset_url: 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 OpenLandMap MCP Server. Nothing to install.
get_asset_url 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 get_asset_url 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 get_asset_url. 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.
get_asset_url is provided by the OpenLandMap MCP Server MCP server (tharlestsa/openlandmap_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 →