create_namespace

Before writing to a project for the first time in a session, call assess_integration_state to understand client URL patterns and integration state. Create a new namespace in a project. IMPORTANT: Call get_project_details first and check existing namespaces before using this tool. Reuse an existin...

Server Localization localization-mcp-server
Category Write
Risk class Medium
Parameters 33 required

What create_namespace does on Localization

AI agents use create_namespace 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.

ParameterTypeRequiredDescription
reason string Yes Why a new namespace is needed. Mention which existing namespaces you checked and why they do not fit. Example: 'Project has no namespaces yet' or 'Existing: com
namespace string Yes Namespace slug (e.g. 'expenses', 'mobile-v2')
projectSlug string Yes Project slug

Parameters from the server's own tool schema.

Why create_namespace needs a policy

The tool creates a new namespace (a reversible structural element) rather than reading data or deleting it. It modifies project state but is not destructive since namespaces can be managed or removed. However, the severity is high because creating inappropriate namespaces could fragment the localization system's architecture and require remediation, affecting many translations and workflows.

From the tool's definition Tool description explicitly states 'Create a new namespace in a project' — a write operation that modifies project architecture.

Questions about create_namespace

What does the create_namespace tool do? +

Before writing to a project for the first time in a session, call assess_integration_state to understand client URL patterns and integration state. Create a new namespace in a project. IMPORTANT: Call get_project_details first and check existing namespaces before using this tool. Reuse an existing namespace whenever context makes the target clear. Do NOT create a new namespace just because the request did not name one explicitly. Creating a namespace is an architectural decision — it must be justified. You MUST provide a non-empty reason explaining why no existing namespace fits. If you cannot state a clear reason, do not create — ask the user instead. Namespace slugs must be lowercase alphanumeric with dashes. 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.

What parameters does create_namespace accept? +

create_namespace accepts 3 parameters: reason, namespace, projectSlug. Required: reason, namespace, projectSlug. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_namespace? +

Register the Localization MCP server in PolicyLayer and add a rule for create_namespace: 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.

What risk level is create_namespace? +

create_namespace is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_namespace? +

Yes. Add a rate_limit block to the create_namespace 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.

How do I block create_namespace completely? +

Set action: deny in the PolicyLayer policy for create_namespace. 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.

What MCP server provides create_namespace? +

create_namespace 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.