AI agents call patents.search 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 retrieves publicly available patent information from the USPTO Open Data Portal. It has no side effects, cannot modify or delete data, and does not execute code or trigger external operations. The search results are informational only. Even though the MCP server involves financial settlement via USDC/Solana, this specific tool does not interact with financial operations—it is a simple read/query operation.
From the tool's definition Tool performs search functionality on USPTO patent data, returning titles, inventors, applicants, status, classification codes, and URLs. No modification, deletion, or execution of external operations is performed—purely data retrieval and query.
Attacks that exploit this kind of access
Search US patent applications and grants (USPTO Open Data Portal). Returns titles, inventors, applicants, status, classification codes, and Patent Center URLs. 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 patents.search: 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.
patents.search 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 patents.search 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 patents.search. 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.
patents.search 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 →