Set patent project directory. Must be called before any other tool.
AI agents use set_root 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 sets a directory path for the patent project, which is a write-like configuration action that can be changed or reset. It has no destructive effects, does not execute code or shell commands, and does not involve financial transactions. While it modifies state, the action is reversible.
From the tool's definition Tool performs a configuration action ('Set patent project directory') that modifies the tool's operational state/context, which is reversible and does not delete or execute external code.
Attacks that exploit this kind of access
Set patent project directory. Must be called before any other tool. 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 set_root: 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.
set_root 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 set_root 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 set_root. 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.
set_root 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 →