AI agents use tag_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.
This tool performs a reversible write operation—adding a tag to a localization key. Tags are metadata that can be modified, removed, or reassigned without destroying underlying translation data. The impact is limited to organizational metadata within a localization project. While it modifies state, the operation is not destructive, does not execute arbitrary code, and poses minimal security risk.
From the tool's definition Tool description: 'Add a tag to a localization key. Creates the tag if it doesn't exist.' The action is to add/create a tag, which modifies metadata associated with a key in a reversible manner.
Attacks that exploit this kind of access
Add a tag to a localization key. Creates the tag if it doesn't exist. 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 tag_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.
tag_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 tag_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 tag_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.
tag_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 →