run_prompt_completion

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.

Server Portkey Admin CodesWhat/portkey-admin-mcp
Category Execute
Risk class High
Parameters 43 required

What run_prompt_completion does on Portkey Admin

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.

ParameterTypeRequiredDescription
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.

Why run_prompt_completion needs a policy

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)

Questions about run_prompt_completion

What does the run_prompt_completion tool do? +

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.

What parameters does run_prompt_completion accept? +

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.

How do I enforce a policy on run_prompt_completion? +

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.

What risk level is run_prompt_completion? +

run_prompt_completion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_prompt_completion? +

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.

How do I block run_prompt_completion completely? +

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.

What MCP server provides run_prompt_completion? +

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.