Create an org-level provider integration. Some backends need provider-specific fields, and the new integration becomes the source for downstream providers and workspace access. Returns the new integration id and slug.
AI agents use create_integration 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 |
|---|---|---|---|
key | string | — | API key for the provider (if required) |
name | string | Yes | Human-readable name for the integration |
slug | string | — | URL-friendly identifier (auto-generated from name if not provided) |
aws_region | string | — | AWS region (for AWS Bedrock) |
api_version | string | — | API version (for Azure OpenAI) |
custom_host | string | — | Custom base URL for the provider |
description | string | — | Optional description of the integration |
workspace_id | string | — | Workspace ID for workspace-scoped integrations |
resource_name | string | — | Resource name (for Azure OpenAI) |
vertex_region | string | — | GCP region (for Vertex AI) |
ai_provider_id | string | Yes | ID of the AI provider (e.g., 'openai', 'anthropic', 'azure-openai', 'aws-bedrock', 'vertex-ai') |
deployment_name | string | — | Deployment name (for Azure OpenAI) |
Parameters from the server's own tool schema.
An AI agent can call create_integration 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 signalsHigh parameter count (15 properties)
Attacks that exploit this kind of access
Create an org-level provider integration. Some backends need provider-specific fields, and the new integration becomes the source for downstream providers and workspace access. Returns the new integration id and slug. 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.
create_integration accepts 12 parameters: key, name, slug, aws_region, api_version, custom_host, description, workspace_id, resource_name, vertex_region, ai_provider_id, deployment_name. Required: name, ai_provider_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 create_integration: 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.
create_integration 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 create_integration 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 create_integration. 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.
create_integration 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.