AI agents call patents.detail 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 performs information retrieval only. It queries patent office records and returns detailed information about a specific patent application. There are no side effects, no data modification, no code execution, and no financial transactions triggered by the tool itself (though the server operates on a pay-per-call model, that is infrastructure-level, not a tool-level concern).
From the tool's definition Tool retrieves patent application details including bibliography, event timeline, continuity chain, assignments, and foreign priority information. All operations are queries/fetches with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Full file-wrapper detail for a US patent application: bibliography, event timeline (filings, Office Actions, allowances), continuity chain (parents, divisionals), assignments, foreign priority. 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.detail: 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.detail 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.detail 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.detail. 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.detail 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 →