Fetch full details of a single TMS job: status, target language, filename, word count, assigned providers, due date, and workflow step. Note: in workflow projects, each step has a distinct job UID, tms_list_jobs returns one entry per step. (GET /api2/v1/projects/{projectUid}/jobs/{jobUid})
AI agents call tms_get_job to retrieve information from Phrase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval operation with no side effects. It queries job metadata from the Phrase localization platform using a GET endpoint, which is inherently a read-only action. The tool returns informational data about a localization job but cannot modify, delete, or execute any operations.
From the tool's definition Tool description explicitly states 'Fetch full details' of a job and uses GET HTTP method. Returns read-only information: status, target language, filename, word count, assigned providers, due date, and workflow step.
Attacks that exploit this kind of access
Fetch full details of a single TMS job: status, target language, filename, word count, assigned providers, due date, and workflow step. Note: in workflow projects, each step has a distinct job UID, tms_list_jobs returns one entry per step. (GET /api2/v1/projects/{projectUid}/jobs/{jobUid}). It is categorised as a Read tool in the Phrase MCP Server, which means it retrieves data without modifying state.
Register the Phrase MCP server in PolicyLayer and add a rule for tms_get_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_get_job is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tms_get_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_get_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_get_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 →