This record as markdown: /tools/delano-postman-mcp-server/fork-collection.md
What fork_collection does on Postman
AI agents use fork_collection 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.
Why fork_collection is rated Medium
Forking a collection creates a new copy (derivative) of an existing collection in a workspace. This is a reversible write operation — it creates new data without modifying or deleting the original. The blast radius is medium since an AI agent could create many unwanted forks across workspaces, cluttering the environment, but no data is destroyed or financial impact incurred.
From the tool's definition Fork a collection to a workspace
Attacks that exploit this kind of access
The rule that runs fork_collection safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Postman, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fork_collection, this is the rule to start with:
fork_collection stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Postman, apply this rule, and every fork_collection call is checked against it from then on.
Questions about fork_collection
Fork a collection to a workspace. 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 fork_collection: 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.
fork_collection 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 fork_collection 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 fork_collection. 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.
fork_collection is provided by the Postman MCP server (delano/postman-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Postman, and thousands of servers like it.
This server
Across the catalogue