Solar irradiance + PV-yield forecast for any coordinate (free/keyless, global). Returns a daily 1-16 day forecast: GHI (kWh/m²), peak sun hours, sunshine hours, and estimated yield per kWp of panels (at a 0.75 performance ratio). For rooftop-solar planning, agrivoltaics, and EV-charge scheduling....
AI agents call energy.solar-forecast to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval tool that queries solar forecast information for a given coordinate and returns historical or predictive analytics. It has no side effects, does not modify or delete data, does not execute code or trigger external operations, and involves no financial transactions. The lowest severity is appropriate given the benign nature of weather/solar data retrieval used for planning purposes.
From the tool's definition Tool 'returns a daily 1-16 day forecast' of solar irradiance and PV-yield data; described as 'free/keyless' with no mention of modifications, deletions, or execution of external systems. It retrieves and queries meteorological and solar performance data.
Attacks that exploit this kind of access
Solar irradiance + PV-yield forecast for any coordinate (free/keyless, global). Returns a daily 1-16 day forecast: GHI (kWh/m²), peak sun hours, sunshine hours, and estimated yield per kWp of panels (at a 0.75 performance ratio). For rooftop-solar planning, agrivoltaics, and EV-charge scheduling. Complements energy.sol. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for energy.solar-forecast: 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. Nothing to install.
energy.solar-forecast 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 energy.solar-forecast 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 energy.solar-forecast. 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.
energy.solar-forecast is provided by the MCP server (@2sio/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 →