AI agents call external_search_patents_by_keyword to retrieve information from IP-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves patent information from the JPO (Japan Patent Office) API. Patent data is publicly available reference information. The operation is read-only with no side effects—it queries but does not modify, delete, or execute arbitrary code.
From the tool's definition Tool name 'external_search_patents_by_keyword' indicates a search/query operation. Server description explicitly states 'query patent data' and 'natural language access to Japanese patent information.' Sibling tools (jpo_fetch_full_record,…
Attacks that exploit this kind of access
external_search_patents_by_keyword. It is categorised as a Read tool in the IP-MCP MCP Server, which means it retrieves data without modifying state.
Register the IP- MCP server in PolicyLayer and add a rule for external_search_patents_by_keyword: 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 IP-MCP. Nothing to install.
external_search_patents_by_keyword 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 external_search_patents_by_keyword 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 external_search_patents_by_keyword. 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.
external_search_patents_by_keyword is provided by the IP- MCP server (kitepon-rgb/ip-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 →