AI agents use update_tag to create or update resources in MCP Auth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Auth environment.
This tool creates or modifies data reversibly by updating an existing tag. It does not delete data (which would be Destructive), execute arbitrary code (which would be Execute), or handle financial transactions (Financial). The modification is reversible since updates can be undone by subsequent updates.
From the tool's definition Tool name 'update_tag' and description 'Update a tag' indicate modification of existing data. The sibling tools show a clear CRUD pattern where 'create_tag' (Write), 'delete_tag' (Destructive), and 'update_tag' (this tool) modify tag entities.
Attacks that exploit this kind of access
Update a tag. It is categorised as a Write tool in the MCP Auth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Auth MCP server in PolicyLayer and add a rule for 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 MCP Auth. Nothing to install.
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 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 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.
update_tag is provided by the MCP Auth MCP server (rubenpenap/mcp-auth). 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 →