AI agents use update_api_tags to create or update resources in Postman — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Postman environment.
This tool creates or modifies API tags, which is a reversible change to metadata. It does not execute code, delete data, or move money. Tags can be updated, removed, or changed without permanent loss of information, making it a Write operation with low severity due to limited blast radius (only affects organizational metadata, not core functionality or data).
From the tool's definition Tool name 'update_api_tags' indicates modification of metadata (tags) associated with an API. The description 'Update tags for an API' confirms this is a write operation that modifies existing data reversibly.
Attacks that exploit this kind of access
Update tags for an API. It is categorised as a Write tool in the Postman MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Postman MCP server in PolicyLayer and add a rule for update_api_tags: 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 Postman. Nothing to install.
update_api_tags 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_api_tags 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_api_tags. 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_api_tags is provided by the Postman MCP server (postmanv3/postman-mcp-server). 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 →