Execute a prompt against the configured model and return the completion. This makes a billable model call, so use render_prompt first when you want to check the template and validate_completion_metadata when billing fields are uncertain.
AI agents invoke run_prompt_completion to trigger actions in Portkey Admin. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
metadata | object | Yes | Billing metadata - client_id, app, env are REQUIRED for cost attribution |
prompt_id | string | Yes | Prompt ID or slug to execute |
variables | object | Yes | Variable values to substitute into the template |
hyperparameters | object | — | Override default hyperparameters |
Parameters from the server's own tool schema.
run_prompt_completion triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsHigh parameter count (16 properties)
Attacks that exploit this kind of access
Execute a prompt against the configured model and return the completion. This makes a billable model call, so use render_prompt first when you want to check the template and validate_completion_metadata when billing fields are uncertain. It is categorised as a Execute tool in the Portkey Admin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_prompt_completion accepts 4 parameters: metadata, prompt_id, variables, hyperparameters. Required: metadata, prompt_id, variables. 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 run_prompt_completion: 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.
run_prompt_completion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_prompt_completion 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 run_prompt_completion. 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.
run_prompt_completion 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.