Compare current weather between two Finnish locations side by side.
AI agents call fi_compare_weather to retrieve information from Mcp Nordic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays weather information for comparison purposes only. It has no side effects—it does not modify data, execute commands, delete records, or commit financial obligations. It is purely a read operation querying a weather API for public meteorological data.
From the tool's definition Tool name 'fi_compare_weather' and description 'Compare current weather between two Finnish locations side by side' indicate retrieval and comparison of publicly available weather data with no modifications, deletions, or external operations triggered.
Attacks that exploit this kind of access
Compare current weather between two Finnish locations side by side. It is categorised as a Read tool in the Mcp Nordic MCP Server, which means it retrieves data without modifying state.
Register the Mcp Nordic MCP server in PolicyLayer and add a rule for fi_compare_weather: 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 Mcp Nordic. Nothing to install.
fi_compare_weather 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 fi_compare_weather 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 fi_compare_weather. 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.
fi_compare_weather is provided by the Mcp Nordic MCP server (robobobby/mcp-nordic). 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 →