Earnings release calendar — which US-listed companies report earnings in a date window, with expected and (once reported) actual EPS and revenue, and the time of day (before/after market). Pass a from/to window (YYYY-MM-DD; defaults to the next 14 days) and optionally a ticker to filter to one co...
AI agents call calendar.earnings 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 read-only data retrieval tool that queries a financial calendar (Finnhub data source). While it provides financial information, it does not move money, execute trades, modify data, or trigger irreversible actions. The agent retrieves historical and scheduled earnings data without side effects.
From the tool's definition Tool retrieves earnings schedule data: 'which US-listed companies report earnings in a date window, with expected and (once reported) actual EPS and revenue'. Operations are 'Pass a from/to window' and 'optionally a ticker to filter' — purely query parameters.
Attacks that exploit this kind of access
Earnings release calendar — which US-listed companies report earnings in a date window, with expected and (once reported) actual EPS and revenue, and the time of day (before/after market). Pass a from/to window (YYYY-MM-DD; defaults to the next 14 days) and optionally a ticker to filter to one company. Agents cannot recall future earnings dates — this is the schedule. Data by Finnhub. 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 calendar.earnings: 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.
calendar.earnings 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 calendar.earnings 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 calendar.earnings. 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.
calendar.earnings 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 →