Historical quarterly earnings surprises for a US-listed company — reported (actual) EPS vs the analyst consensus estimate, the absolute surprise, and the surprise percentage, for the most recent quarters (newest first). Pass ticker (optionally limit). Tells you whether a company has been beating ...
AI agents call stocks.earnings-surprises 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 financial data without any side effects. It provides read-only access to historical earnings information indexed by company ticker. While the server itself is financial in nature (pay-per-call on blockchain), this specific tool only retrieves and compares publicly available earnings data. There is no capability to move money, execute trades, modify data, or trigger external operations.
From the tool's definition Tool retrieves historical quarterly earnings data (actual EPS, consensus estimates, surprise metrics) for analysis. Key phrases: 'Historical quarterly earnings surprises', 'reported (actual) EPS vs analyst consensus', 'for the most recent quarters'.
Attacks that exploit this kind of access
Historical quarterly earnings surprises for a US-listed company — reported (actual) EPS vs the analyst consensus estimate, the absolute surprise, and the surprise percentage, for the most recent quarters (newest first). Pass ticker (optionally limit). Tells you whether a company has been beating or missing expectations. 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 stocks.earnings-surprises: 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.
stocks.earnings-surprises 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 stocks.earnings-surprises 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 stocks.earnings-surprises. 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.
stocks.earnings-surprises 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 →