AI agents use tms_update_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.
The tool creates or modifies data reversibly by updating an existing job. It is not destructive (does not delete), does not execute arbitrary code, and does not involve financial transactions. The 'mutates data' language and PUT semantics clearly indicate a Write operation.
From the tool's definition Tool description explicitly states 'This operation mutates data' and uses HTTP PUT method to update a job resource in the Phrase TMS API. The endpoint pattern /api2/v1/projects/{projectUid}/jobs/{jobUid} indicates modification of an existing job entity.
Attacks that exploit this kind of access
Update a Phrase TMS job (PUT /api2/v1/projects/{projectUid}/jobs/{jobUid}). This operation mutates data. 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 tms_update_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.
tms_update_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 tms_update_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 tms_update_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.
tms_update_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 →