Extract citation-grounded claims from a 10-K section.
AI agents call tenk.extract_section to retrieve information from Mcp Financial Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and extracts information from 10-K filings without altering data, executing queries, or triggering financial transactions. It is a data retrieval operation that returns structured claims grounded in document citations. No side effects or irreversible actions are performed.
From the tool's definition Tool description states 'Extract citation-grounded claims from a 10-K section' — this performs retrieval and parsing of existing financial document sections with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Extract citation-grounded claims from a 10-K section. It is categorised as a Read tool in the Mcp Financial Data MCP Server, which means it retrieves data without modifying state.
Register the Mcp Financial Data MCP server in PolicyLayer and add a rule for tenk.extract_section: 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 Financial Data. Nothing to install.
tenk.extract_section 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 tenk.extract_section 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 tenk.extract_section. 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.
tenk.extract_section is provided by the Mcp Financial Data MCP server (sebaustin/mcp-financial-data). 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 →