AI agents call get_collection_roles to retrieve information from Postman without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about roles assigned to a collection in Postman. It performs a query operation with no side effects, no data modification, and no irreversible actions. It falls squarely into the Read category as it only fetches existing data.
From the tool's definition Tool name 'get_collection_roles' and description 'Get roles for a collection' indicate data retrieval without modification. The verb 'get' is explicitly a read operation that queries existing role information.
Attacks that exploit this kind of access
Get roles for a collection. It is categorised as a Read tool in the Postman MCP Server, which means it retrieves data without modifying state.
Register the Postman MCP server in PolicyLayer and add a rule for get_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.
get_collection_roles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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 →