AI agents use update_request 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.
The tool modifies existing data (a request within a Postman collection) but does not delete or destroy it. This is reversible—the previous version can be restored. It falls into the Write category. Severity is medium because modifying requests could affect API workflows, but the impact is contained to the specific request and is not permanent.
From the tool's definition Tool name is 'update_request' and description states 'Update an existing request in a collection', indicating modification of existing data.
Documented attack patterns abuse exactly the kind of access update_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Postman, and nothing reaches the server without passing your rules. This is the rule we recommend for update_request:
{
"version": "1",
"default": "deny",
"tools": {
"update_request": {
"limits": [
{
"counter": "update_request_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_request 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.
Free to start. No card required.
Update an existing request in a collection. 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_request: 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_request 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_request 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_request. 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_request is provided by the Postman MCP server (salehkhatri/postman-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Postman tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
19 Postman tools catalogued and risk-classified — across an index of 42,500+ MCP servers.