AI agents use create_key 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.
Creating a translation key is a reversible modification (keys can be deleted via 'delete_keys'), with no financial impact or code execution. The severity is medium because mistaken mass key creation could clutter a localization project and require cleanup, but the operation is undoable and scoped to project metadata rather than live user-facing content.
From the tool's definition Tool name 'create_key' indicates creation of a new translation key; sibling tools include 'delete_keys', 'create_or_update_translations', and 'create_project', all of which modify localization data.
Attacks that exploit this kind of access
create_key. 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_key: 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_key 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_key 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_key. 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_key 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 →