glossary · Patentorney MCP: Risk & Policy

WHAT IT DOES

What glossary does on Patentorney

AI agents use glossary 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.

WHY IT NEEDS A POLICY

Why glossary needs a policy

The tool supports multiple operations including add, update, and remove on glossary entries. 'Remove' could be considered destructive, but glossary entries in a patent draft system are typically reversible (can be re-added). The most severe routine operations are write-level (add/update). 'Remove' elevates concern but without indication of irreversibility, Write is the best fit.

From the tool's definition Glossary: add|get|update|remove|list — supports add, update, remove operations alongside read operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

glossary Rate-limited

glossary stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "glossary": {
      "limits": [
        {
          "counter": "glossary_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Patentorney, so you can run agents against it safely.

FAQ

Questions about glossary

What does the glossary tool do? +

Glossary: add|get|update|remove|list. 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.

How do I enforce a policy on glossary? +

Register the Patentorney MCP server in PolicyLayer and add a rule for glossary: 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.

What risk level is glossary? +

glossary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit glossary? +

Yes. Add a rate_limit block to the glossary 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.

How do I block glossary completely? +

Set action: deny in the PolicyLayer policy for glossary. 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.

What MCP server provides glossary? +

glossary 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.