AI agents use create_language to create or update resources in Tolgee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tolgee environment.
This tool creates a new language in a Tolgee localization project, which is a reversible modification of project state. It falls under the Write category (creates data). Severity is medium because while the action is reversible (languages can be deleted), misconfiguration of languages in a localization project could impact translation workflows and project structure, affecting downstream systems that depend on…
From the tool's definition Tool name 'create_language' and description 'Add a new language' indicate a create operation that modifies project configuration by introducing a new language resource.
Attacks that exploit this kind of access
Add a new language to a Tolgee project. It is categorised as a Write tool in the Tolgee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tolgee MCP server in PolicyLayer and add a rule for create_language: 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 Tolgee. Nothing to install.
create_language 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_language 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_language. 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_language is provided by the Tolgee MCP server (ytarfa/tolgee-mcp). 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 →