create_prompt

Create a new prompt template and initial version. Use this for first-time setup; use migrate_prompt for idempotent CI/CD flows. Accepts plain text or structured chat messages, creates a new version immediately, and returns the prompt id, slug, and version id. For multi-message chat prompts pass m...

Server Portkey Admin CodesWhat/portkey-admin-mcp
Category Write
Risk class Medium
Parameters 123 required

What create_prompt does on Portkey Admin

AI agents use create_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.

ParameterTypeRequiredDescription
name string Yes Display name for the prompt
model string Model identifier (e.g., 'gpt-4', 'claude-3-opus'). Required unless ai_model_id or finetune_id is provided
tools array Tool definitions for tool use
string string Legacy prompt template string. Use plain text for single-message prompts, or a JSON-encoded messages array string for multi-message chat prompts.
dry_run boolean When true, validate without creating
messages array Structured chat template alias. Serialized to the legacy string format before creation.
functions array Function definitions for function calling
parameters object Yes Default values for template variables
ai_model_id string AI model ID (alternative to model). Required unless model or finetune_id is provided
finetune_id string Fine-tune ID (alternative to model). Required unless model or ai_model_id is provided
tool_choice object Tool choice strategy
virtual_key string Yes Virtual key slug for model access

Parameters from the server's own tool schema.

Why create_prompt needs a policy

An AI agent can call create_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.

Risk signalsAccepts raw HTML/template content (messages[].content) · High parameter count (29 properties)

Questions about create_prompt

What does the create_prompt tool do? +

Create a new prompt template and initial version. Use this for first-time setup; use migrate_prompt for idempotent CI/CD flows. Accepts plain text or structured chat messages, creates a new version immediately, and returns the prompt id, slug, and version id. For multi-message chat prompts pass messages (preferred) or a JSON-encoded array as string. 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.

What parameters does create_prompt accept? +

create_prompt accepts 12 parameters: name, model, tools, string, dry_run, messages, functions, parameters, ai_model_id, finetune_id, tool_choice, virtual_key. Required: name, parameters, virtual_key. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_prompt? +

Register the Portkey Admin MCP server in PolicyLayer and add a rule for create_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.

What risk level is create_prompt? +

create_prompt is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_prompt? +

Yes. Add a rate_limit block to the create_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.

How do I block create_prompt completely? +

Set action: deny in the PolicyLayer policy for create_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.

What MCP server provides create_prompt? +

create_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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.