AI agents use kinbox_update_tag to create or update resources in Kinbox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kinbox environment.
This tool modifies existing tags reversibly—tags can be updated again or deleted, so it is not destructive. It performs a write operation on tag metadata within the Kinbox customer service platform. Severity is medium because tag updates affect organization/categorization of contacts and campaigns but do not directly impact financial transactions, customer communication content, or irreversible deletions.
From the tool's definition Tool name 'kinbox_update_tag' and description 'Atualiza uma tag existente' (Updates an existing tag) indicate modification of existing data.
Attacks that exploit this kind of access
Atualiza uma tag existente. It is categorised as a Write tool in the Kinbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kinbox MCP server in PolicyLayer and add a rule for kinbox_update_tag: 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 Kinbox. Nothing to install.
kinbox_update_tag 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 kinbox_update_tag 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 kinbox_update_tag. 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.
kinbox_update_tag is provided by the Kinbox MCP server (vergamini65-boop/kinbox-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 →