AI agents use update_collection_roles 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 modifies collection role assignments, which is a Write operation (reversible configuration change). It does not delete roles (Destructive), execute code (Execute), or move money (Financial). Severity is medium because role misconfiguration could grant unintended access to collections, but the operation is reversible and scoped to role metadata rather than collection data itself.
From the tool's definition Tool name 'update_collection_roles' and description 'Update collection roles' indicate modification of access control metadata. The parenthetical '(requires EDITOR role)' confirms this modifies permissions/roles rather than deleting them.
Attacks that exploit this kind of access
Update collection roles (requires EDITOR role). 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_collection_roles: 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_collection_roles 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_collection_roles 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_collection_roles. 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_collection_roles 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 →