AI agents call get_metrics 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 performs a straightforward read operation to fetch financial metrics from the SEC database. No data is created, modified, deleted, or used to trigger external operations. The blast radius of misuse is minimal: an agent could only retrieve publicly available financial data already published by the SEC. There are no side effects on any system or financial accounts.
From the tool's definition Tool retrieves '40+ financial ratios and metrics for a US public company' - a data retrieval operation with no modification or execution capability. The description indicates queries of pre-computed financial metrics (ROE, ROIC, etc.) from SEC financial data.
Attacks that exploit this kind of access
40+ financial ratios and metrics for a US public company: ROE, ROIC,. 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_metrics: 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_metrics 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_metrics 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_metrics. 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_metrics 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 →