AI agents call get_trademark_class_info to retrieve information from USPTO Patent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve trademark classification data without modifying, deleting, or executing operations. The naming convention 'get_' is consistent with sibling Read tools like 'get_citation_metrics', 'get_cpc_info', etc. No evidence of side effects, execution, financial transactions, or destructive operations. Confidence is moderate (0.85) due to missing description, but the pattern is clear from context.
From the tool's definition Tool name 'get_trademark_class_info' indicates retrieval of classification information. Server description confirms this is a data retrieval tool for USPTO information.
Documented attack patterns abuse exactly the kind of access get_trademark_class_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and USPTO Patent MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_trademark_class_info:
{
"version": "1",
"default": "deny",
"tools": {
"get_trademark_class_info": {}
}
}get_trademark_class_info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_trademark_class_info. It is categorised as a Read tool in the USPTO Patent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USPTO Patent MCP Server MCP server in PolicyLayer and add a rule for get_trademark_class_info: 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 USPTO Patent MCP Server. Nothing to install.
get_trademark_class_info 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_trademark_class_info 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_trademark_class_info. 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_trademark_class_info is provided by the USPTO Patent MCP Server MCP server (riemannzeta/patent_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 61 USPTO Patent MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
61 USPTO Patent MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.