AI agents use strings_update_branch 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.
This tool modifies an existing branch (e.g., renaming it) but does not permanently delete or destroy data. The update is reversible—a renamed branch can be renamed again. It does not execute arbitrary code, access financial systems, or irreversibly delete data. It represents a Write operation with medium severity due to potential impact on project organization and collaboration workflows in a localization system.
From the tool's definition Tool name 'strings_update_branch' and description 'Update an existing branch in a Phrase Strings project (e.g. rename it)' indicates modification of existing data.
Attacks that exploit this kind of access
Update an existing branch in a Phrase Strings project (e.g. rename it). 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.
Register the Phrase MCP server in PolicyLayer and add a rule for strings_update_branch: 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.
strings_update_branch 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 strings_update_branch 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 strings_update_branch. 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.
strings_update_branch 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.
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 →