AI agents use strings_create_job 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.
Creating a job in a localization system modifies project state by adding a new work item. This is reversible (jobs can typically be deleted or cancelled), so it falls under Write rather than Destructive. Severity is medium because job creation could trigger downstream processes (like task assignments or automated workflows) and affect team operations, but the blast radius is localized to a single project.
From the tool's definition Tool name includes 'create' and description states 'Create a job in a Phrase Strings project' — this creates a new resource within the localization platform.
Attacks that exploit this kind of access
Create a job in a Phrase Strings project. 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_create_job: 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_create_job 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_create_job 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_create_job. 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_create_job 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 →