Create a new translation project on the localization backend. Only call this after the user has explicitly confirmed they want to create a project. The slug must be unique — if a project with this slug already exists, the call will fail. At least one namespace is required — provide it in the name...
AI agents use create_project to create or update resources in Localization — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Localization environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Optional human-readable project name (e.g. 'My Application'). Shown in Admin UI. |
slug | string | Yes | Project slug — short, lowercase, hyphen-separated identifier (e.g. 'my-app', 'travis-v2'). Must be unique. |
locales | array | Yes | Target locales to create besides the default 'en'. Supported: ar, bg, cs, da, de, el, es, et, fi, fr, hi, hr, hu, id, is, it, ja, ko, lt, lv, ms, nb, nl, pl, pt |
namespaces | array | Yes | List of namespace slugs to create (e.g. ['common'] or ['backoffice-translations', 'mobile']). At least one is required. |
Parameters from the server's own tool schema.
This tool creates new projects in a localization system, which is a reversible Write operation (projects can presumably be deleted or modified later). It does not execute arbitrary code, delete data, or move money.
From the tool's definition Tool description states 'Create a new translation project on the localization backend' — this creates new data in a backend system.
Attacks that exploit this kind of access
Create a new translation project on the localization backend. Only call this after the user has explicitly confirmed they want to create a project. The slug must be unique — if a project with this slug already exists, the call will fail. At least one namespace is required — provide it in the namespaces array. At least one target locale is required — these are the languages you want to translate INTO (besides "en" which is auto-created as default). Supported locale codes: ar, bg, cs, da, de, el, es, et, fi, fr, hi, hr, hu, id, is, it, ja, ko, lt, lv, ms, nb, nl, pl, pt, ro, sk, sl, sr, sv, th, tr, uk, vi, zh. You can also pass any valid 2-3 char ISO 639 code not in this list. Sandbox is auto-initialized and ready for writes immediately after project creation. It is categorised as a Write tool in the Localization MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_project accepts 4 parameters: name, slug, locales, namespaces. Required: slug, locales, namespaces. The full parameter table on this page comes from the server's own tool schema.
Register the Localization MCP server in PolicyLayer and add a rule for 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 Localization. Nothing to install.
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 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 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.
create_project is provided by the Localization MCP server (localization-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 →