strings_update_glossary_term · Phrase MCP: Risk & Policy

WHAT IT DOES

What strings_update_glossary_term does on Phrase

AI agents use strings_update_glossary_term to create or update resources in Phrase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Phrase environment.

WHY IT NEEDS A POLICY

Why strings_update_glossary_term needs a policy

This tool modifies glossary terms in a localization database. The 'update' operation is reversible (the term can be updated again to a previous value or corrected), making it a Write action rather than Destructive. The blast radius is medium because corrupted glossary terms could affect translation quality across projects, but the damage can be undone by updating the terms again.

From the tool's definition Tool name contains 'update' and description states 'Update an existing term in a Phrase Strings term base (glossary)', indicating modification of existing data in a reversible manner.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

strings_update_glossary_term Rate-limited

strings_update_glossary_term 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": {
    "strings_update_glossary_term": {
      "limits": [
        {
          "counter": "strings_update_glossary_term_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 Phrase, so you can run agents against it safely.

FAQ

Questions about strings_update_glossary_term

What does the strings_update_glossary_term tool do? +

Update an existing term in a Phrase Strings term base (glossary). It is categorised as a Write tool in the Phrase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on strings_update_glossary_term? +

Register the Phrase MCP server in PolicyLayer and add a rule for strings_update_glossary_term: 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 Phrase. Nothing to install.

What risk level is strings_update_glossary_term? +

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

Can I rate-limit strings_update_glossary_term? +

Yes. Add a rate_limit block to the strings_update_glossary_term 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 strings_update_glossary_term completely? +

Set action: deny in the PolicyLayer policy for strings_update_glossary_term. 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 strings_update_glossary_term? +

strings_update_glossary_term is provided by the Phrase MCP server (phrase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.