AI agents call get_income_statement to retrieve information from Secfinapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries financial statement data from the SEC Financial API. It fetches existing information without creating, modifying, deleting, or executing operations. The sibling tools (get_balance_sheet, get_cash_flow, get_company_info, get_metrics, list_companies) all follow a 'get/list' pattern, further confirming this is a read-only data access tool with minimal risk.
From the tool's definition Tool name 'get_income_statement' and description indicate retrieval of standardized financial data (revenue, cost of revenue, operating...). The verb 'get' and context of querying SEC financial data confirms read-only data retrieval with no side effects.
Attacks that exploit this kind of access
Standardized income statement (revenue, cost of revenue, operating. It is categorised as a Read tool in the Secfinapi MCP Server, which means it retrieves data without modifying state.
Register the Secfinapi MCP server in PolicyLayer and add a rule for get_income_statement: 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 Secfinapi. Nothing to install.
get_income_statement 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 get_income_statement 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 get_income_statement. 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.
get_income_statement is provided by the Secfinapi MCP server (michalperni11-gif/secfinapi-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 →