Search USPTO patent database for AI-related filings: applicant companies, patent titles, abstract summaries, filing dates, and technology classification. Reveals who is building what in neural networks, autonomous agents, and LLMs. Use this tool when: - A research agent is building a competitive ...
AI agents call get_ai_patents to retrieve information from Omni Service Node without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a public patent database and returns information only. USPTO patents are public record. No data is created, modified, deleted, or executed; no external operations are triggered; no financial transactions occur. It is purely informational retrieval. The low severity reflects minimal blast radius—patent information is already public and cannot be harmed by over-querying or misuse.
From the tool's definition Tool performs database search of USPTO patent records (public filings) to retrieve applicant companies, titles, abstracts, filing dates, and classifications.
Attacks that exploit this kind of access
Search USPTO patent database for AI-related filings: applicant companies, patent titles, abstract summaries, filing dates, and technology classification. Reveals who is building what in neural networks, autonomous agents, and LLMs. Use this tool when: - A research agent is building a competitive intelligence map of AI patent activity - An investor agent wants to assess a company. It is categorised as a Read tool in the Omni Service Node MCP Server, which means it retrieves data without modifying state.
Register the Omni Service Node MCP server in PolicyLayer and add a rule for get_ai_patents: 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 Omni Service Node. Nothing to install.
get_ai_patents 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_ai_patents 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_ai_patents. 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_ai_patents is provided by the Omni Service Node MCP server (luckkyyy23/omni-service-node). 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 →