Create a new Phrase TMS project from scratch. Requires Project Manager permissions. For most use cases, prefer tms_create_project_from_template_shorthand instead, which applies pre-configured settings. Use this only when no suitable template exists. (POST /api2/v3/projects)
AI agents use tms_create_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 a new project resource in the Phrase TMS system, which is a reversible modification (projects can be deleted). It requires Project Manager permissions, indicating elevated access is needed. The blast radius is high because creating projects could impact organizational localization workflows, resource allocation, and potentially incur costs through project setup and management overhead.
From the tool's definition Tool name contains 'create' and description states 'Create a new Phrase TMS project from scratch'. The endpoint is POST /api2/v3/projects, a standard write operation.
Attacks that exploit this kind of access
Create a new Phrase TMS project from scratch. Requires Project Manager permissions. For most use cases, prefer tms_create_project_from_template_shorthand instead, which applies pre-configured settings. Use this only when no suitable template exists. (POST /api2/v3/projects). 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_create_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_create_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_create_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_create_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_create_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 →