AI agents use strings_merge_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.
Merging is a write operation that modifies project data (the main branch) by integrating another branch's changes. While the operation is reversible (can be undone via revert/reset), it materially changes the state of the codebase and affects all dependent systems.
From the tool's definition Tool performs 'Merge an existing branch into the main branch' — this modifies the main branch state by incorporating changes from another branch, a reversible version control operation.
Attacks that exploit this kind of access
Merge an existing branch into the main branch of a Phrase Strings project. Note: Merging may take several minutes depending on diff size. 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_merge_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_merge_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_merge_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_merge_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_merge_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 →