fetch_era5_pressure_levels
AI agents call fetch_era5_pressure_levels to retrieve information from Era5 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ERA5 climate pressure level data from a public climate data store. It performs a read-only operation (fetch) with no ability to modify, delete, or execute code. The blast radius of misuse is minimal—the worst outcome would be excessive downloads or unauthorized access to publicly available climate data, which is low severity.
From the tool's definition Tool name contains 'fetch' and sibling tools include 'fetch_era5_single_levels' and 'inspect_netcdf', which are clearly read-only data retrieval operations.
Documented attack patterns abuse exactly the kind of access fetch_era5_pressure_levels gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Era5, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_era5_pressure_levels:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_era5_pressure_levels": {}
}
}fetch_era5_pressure_levels is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
fetch_era5_pressure_levels. It is categorised as a Read tool in the Era5 MCP Server, which means it retrieves data without modifying state.
Register the Era5 MCP server in PolicyLayer and add a rule for fetch_era5_pressure_levels: 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 Era5. Nothing to install.
fetch_era5_pressure_levels 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 fetch_era5_pressure_levels 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 fetch_era5_pressure_levels. 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.
fetch_era5_pressure_levels is provided by the Era5 MCP server (swnesbitt/era5-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Era5, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Era5 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.