Update an existing Phrase TMS project settings such as name, due date, or note. To change project status (e.g. mark Completed), use tms_set_project_status instead. (PUT /api2/v2/projects/{projectUid})
AI agents use tms_update_project 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 creates or modifies data (project settings) in a reversible manner. It does not delete data (which would be Destructive), execute arbitrary code (Execute), nor move money (Financial). The severity is medium because misconfiguration of project settings could impact workflow and team coordination, but changes are reversible and don't affect financial transactions or destroy data.
From the tool's definition Tool name contains 'update' and description explicitly states 'Update an existing Phrase TMS project settings such as name, due date, or note.' This is a PUT request that modifies project metadata reversibly.
Attacks that exploit this kind of access
Update an existing Phrase TMS project settings such as name, due date, or note. To change project status (e.g. mark Completed), use tms_set_project_status instead. (PUT /api2/v2/projects/{projectUid}). 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_project: 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_project 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_project 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_project. 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_project 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 →