AI agents call sunrise.compute 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 tool queries and returns calculated astronomical data (sunrise times, sunset times, solar noon, twilight phases) based on provided parameters. It has no side effects on data or systems—it performs a read-only computation and returns results. Despite the server's financial nature (pay-per-call USDC settlement), the tool itself performs only informational lookups and calculations.
From the tool's definition Tool 'sunrise.compute' performs astronomical calculations and retrieves computed sunrise/sunset times and twilight data based on coordinates and date inputs.
Attacks that exploit this kind of access
Astronomically compute sunrise, sunset, solar noon, and civil/nautical/astronomical twilights for a coord + date. 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 sunrise.compute: 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.
sunrise.compute 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 sunrise.compute 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 sunrise.compute. 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.
sunrise.compute 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 →