Prior art & IDS: add|get|update|remove|list|ids_add|ids_list|ids_check.
AI agents use prior_art to create or update resources in Patentorney — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Patentorney environment.
This tool manages prior art references and Information Disclosure Statements (IDS) in a patent application. It supports add, update, and remove operations (Write/Destructive) as well as read operations (get, list, ids_list, ids_check). 'remove' could be considered destructive, but in the context of a document drafting system, changes are typically reversible (managed in structured YAML/LaTeX drafts).
From the tool's definition Prior art & IDS: add|get|update|remove|list|ids_add|ids_list|ids_check
Attacks that exploit this kind of access
Prior art & IDS: add|get|update|remove|list|ids_add|ids_list|ids_check. It is categorised as a Write tool in the Patentorney MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Patentorney MCP server in PolicyLayer and add a rule for prior_art: 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 Patentorney. Nothing to install.
prior_art is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the prior_art 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 prior_art. 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.
prior_art is provided by the Patentorney MCP server (retospect/patentorney-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 →