USPTO patent activity associated with a public company. Pass ticker and optionally a from/to window (YYYY-MM-DD; defaults to ~2 years); returns each record with the application number, patent number (when granted), the filing company name(s), description/title, patent type, filing status, filing ...
AI agents call stocks.patents 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.
The tool queries and returns historical patent information from public USPTO records. It performs a read-only lookup with optional filtering by ticker and date range. There are no side effects, no data modification, no code execution, and no financial transactions. The severity is low because the data is already public and querying it poses minimal risk even if misused by an AI agent.
From the tool's definition Tool retrieves USPTO patent activity data for public companies—'returns each record with the application number, patent number...filing and publication dates, and a document URL.' This is a data query operation with no modification, deletion, or execution…
Attacks that exploit this kind of access
USPTO patent activity associated with a public company. Pass ticker and optionally a from/to window (YYYY-MM-DD; defaults to ~2 years); returns each record with the application number, patent number (when granted), the filing company name(s), description/title, patent type, filing status, filing and publication dates, and a document URL. A company-level innovation/R&D signal (distinct from our key. 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.patents: 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.patents 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.patents 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.patents. 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.patents 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 →