FPD_get_guidance
AI agents call FPD_get_guidance to retrieve information from USPTO Final Petition Decisions 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 designed to retrieve or query guidance information (a Read operation), with no evidence of creating, modifying, deleting, or executing actions. The empty description lowers confidence, but the sibling tools (Search_petitions_*, Get_petition_details, FPD_get_document_*) establish a clear read-only pattern for this server.
From the tool's definition Tool name 'FPD_get_guidance' strongly suggests retrieval of guidance information from the USPTO Final Petition Decisions API.
Attacks that exploit this kind of access
FPD_get_guidance. It is categorised as a Read tool in the USPTO Final Petition Decisions MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USPTO Final Petition Decisions MCP Server MCP server in PolicyLayer and add a rule for FPD_get_guidance: 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 Final Petition Decisions MCP Server. Nothing to install.
FPD_get_guidance 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 FPD_get_guidance 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 FPD_get_guidance. 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.
FPD_get_guidance is provided by the USPTO Final Petition Decisions MCP Server MCP server (john-walkoe/uspto_fpd_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 →