Search US trademarks by wordmark text, owner, or goods/services — the text search the USPTO offers no public API for. Pass query for full-text (best-match ranked), or serial / registrationNumber for an exact record. Filter by field (mark|owner|all), status (live=registered+pending, default; all i...
AI agents call law.trademark-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 queries and retrieves trademark information from USPTO records without creating, modifying, deleting, or executing any operations. It is purely a read operation that provides access to public trademark data through text and field filtering. No side effects or state changes occur.
From the tool's definition Tool performs search and retrieval operations ('Search US trademarks', 'Pass query for full-text', 'Returns wordmark, serial, registration number') with no modification or deletion capabilities. Returns public USPTO trademark data.
Attacks that exploit this kind of access
Search US trademarks by wordmark text, owner, or goods/services — the text search the USPTO offers no public API for. Pass query for full-text (best-match ranked), or serial / registrationNumber for an exact record. Filter by field (mark|owner|all), status (live=registered+pending, default; all includes dead), and intlClass (Nice class). Returns wordmark, serial, registration number, status (+ live flag), dates, owner, classes, and goods/services. Use law.trademark-status for live USPTO prosecution detail on a known serial. 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 law.trademark-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.
law.trademark-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 law.trademark-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 law.trademark-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.
law.trademark-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 →