Get spatial (gridded) climate data for a country at a specific warming level. Returns full per-cell grid data (lat/lon/value/agreement), statistics, and country boundary (TopoJSON from world-atlas) for map rendering. Output includes a JSON block that can be used directly for D3/SVG visualizations...
Part of the Climate Impacts server.
Free to start. No card required.
AI agents call get_spatial_data to retrieve information from Climate Impacts without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_spatial_data only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_spatial_data": {}
}
}See the full Climate Impacts policy for all 8 tools.
These attack patterns abuse exactly the kind of access get_spatial_data gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get spatial (gridded) climate data for a country at a specific warming level. Returns full per-cell grid data (lat/lon/value/agreement), statistics, and country boundary (TopoJSON from world-atlas) for map rendering. Output includes a JSON block that can be used directly for D3/SVG visualizations. RENDERING INSTRUCTIONS: The response includes a boundary field with the country's TopoJSON border. You MUST use it as a clip path — do NOT fetch country borders from any external URL. Each grid cell is a 0.5deg x 0.5deg rectangle. Clip all grid cells to the boundary outline (D3: clipPath + topojson.feature) before rendering. NEVER filter, crop, or omit grid cells — render ALL cells including zeros and low values. Use a continuous color scale so zeros appear as the lightest shade, not gaps. Args: country_iso: ISO 3166-1 alpha-3 country code. See climate://countries resource for all valid codes. variable: Climate variable ID (e.g. 'tasAdjust', 'prAdjust'). See climate://variables resource for all valid IDs — do NOT guess. warming_level: Global warming level in degrees C (1.5, 2.0, 2.5, or 3.0). scenario: Emission scenario ID. Default: 'h_cpol'. See climate://scenarios resource for all valid IDs. season: Season. Default: 'annual'.. It is categorised as a Read tool in the Climate Impacts MCP Server, which means it retrieves data without modifying state.
Register the Climate Impacts MCP server in PolicyLayer and add a rule for get_spatial_data: 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 Climate Impacts. Nothing to install.
get_spatial_data 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_spatial_data 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_spatial_data. 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_spatial_data is provided by the Climate Impacts MCP server (valentinlemaire/climate-impacts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Climate Impacts tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.