Copy a prompt from one environment to another and create or update the target automatically. Use this for staged releases when you want the target prompt synchronized without manual edits, and it returns both source and target version ids.
AI agents use promote_prompt to create or update resources in Portkey Admin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Portkey Admin environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
target_env | string | Yes | Environment identifier (REQUIRED). Use your environment name, for example 'dev', 'staging', 'prod', or 'qa'. |
target_name | string | — | Target prompt name (defaults to source name with env suffix replaced) |
virtual_key | string | — | Virtual key ID to use (defaults to source prompt's virtual_key) |
source_prompt_id | string | Yes | Source prompt ID or slug (e.g., staging prompt) |
target_collection_id | string | Yes | Target collection ID for the promoted prompt |
Parameters from the server's own tool schema.
An AI agent can call promote_prompt faster than any human can review — one bad instruction and it creates or modifies resources in Portkey Admin by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Copy a prompt from one environment to another and create or update the target automatically. Use this for staged releases when you want the target prompt synchronized without manual edits, and it returns both source and target version ids. It is categorised as a Write tool in the Portkey Admin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
promote_prompt accepts 5 parameters: target_env, target_name, virtual_key, source_prompt_id, target_collection_id. Required: target_env, source_prompt_id, target_collection_id. The full parameter table on this page comes from the server's own tool schema.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for promote_prompt: 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 Portkey Admin. Nothing to install.
promote_prompt 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 promote_prompt 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 promote_prompt. 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.
promote_prompt is provided by the Portkey Admin MCP server (CodesWhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.