Create or Update Integration Provider

Endpoint: POST /api/integrations/provider/{name}

Creates a new integration provider or updates an existing one in the Conductor cluster.

Path Parameters

Parameter	Description	Type	Required/ Optional
name	A unique name for the integration provider.	string	Required.

Request Body

Format the request body as a JSON object with the following parameters:

Parameter	Description	Type	Required/ Optional
type	The integration type. Cannot be changed after creation. Supported values: ollama azure_openai openai perplexity grok cohere mistral anthropic vertex_ai vertex_ai_gemini huggingface aws_bedrock_anthropic aws_bedrock_cohere aws_bedrock_titan pineconedb weaviatedb pgvectordb mongovectordb amqp kafka nats aws_sqs azure_service_bus gcp_pubsub ibm_mq aws gcp relational_db sendgrid git	string	Optional.
category	The category of the integration. Supported values: AI_MODEL: For AI/LLM integrations. VECTOR_DB: For Vector database integrations. MESSAGE_BROKER: For message broker integrations. CLOUD: For cloud provider integrations. RELATIONAL_DB: For relational database integrations. GIT: For Git repository integrations. EMAIL: For email provider integrations.	string	Optional.
description	A description for the integration.	string	Optional.
enabled	Whether the integration is active and available for use.	boolean	Optional.
configuration	A key-value map of provider-specific configuration, such as API keys and endpoints. Keys and required values vary by integration type. See Configuration keys by integration type.	object	Optional.

Configuration keys by integration type

The configuration object is a key-value map of provider-specific configuration, such as API keys and endpoints. Keys and required values vary by integration type.

Parameter	Required keys	Optional keys
ollama	endpoint	header, api_key
azure_openai	api_key, endpoint	-
openai	api_key	endpoint,organizationId
perplexity	api_key	–
grok	api_key	-
cohere	api_key, endpoint	–
mistral	api_key, endpoint	–
anthropic	api_key, endpoint	completionsPath, version, betaVersion
vertex_ai	projectName, environment, publisher, file	–
vertex_ai_gemini	projectName, environment, file	–
huggingface	api_key, namespace	–
aws_bedrock_anthropic	connectionType, region Based on the `connectionType` value, the following additional keys may be required: ACCESS_KEY: Requires user (access key) and api_key (access secret). EXTERNAL_ROLE: Requires roleArn and externalId. CONDUCTOR_ROLE: No additional keys required.	awsAccountId
aws_bedrock_cohere	connectionType, region Based on the `connectionType` value, the following additional keys may be required: ACCESS_KEY: Requires user (access key) and api_key (access secret). EXTERNAL_ROLE: Requires roleArn and externalId. CONDUCTOR_ROLE: No additional keys required.	awsAccountId
aws_bedrock_titan	connectionType, region Based on the `connectionType` value, the following additional keys may be required: ACCESS_KEY: Requires user (access key) and api_key (access secret). EXTERNAL_ROLE: Requires roleArn and externalId. CONDUCTOR_ROLE: No additional keys required.	awsAccountId
pineconedb	api_key, projectName, environment	–
weaviatedb	api_key, endpoint	–
pgvectordb	user, password, datasourceURL, dimensions, distance_metric, indexing_method	inverted_list_count
mongovectordb	endpoint, namespace, dimensions, distance_metric	inverted_list_count
amqp	protocol, user, password, endpoint, port, namespace	–
kafka	endpoint, connectionType, protocol	groupId
nats	endpoint, connectionType, authenticationType, protocol, tls	–
aws_sqs	connectionType, region Based on the `connectionType` value, the following additional keys may be required: ACCESS_KEY: Requires user (access key) and api_key (access secret). EXTERNAL_ROLE: Requires roleArn and externalId. CONDUCTOR_ROLE: No additional keys required.	awsAccountId
azure_service_bus	connectionType	endpoint, namespace
gcp_pubsub	projectName, location, file	–
ibm_mq	endpoint, port, queueManager, channel, protocol, pubSubMethod, authenticationType, tls	–
aws	connectionType, region Based on the `connectionType` value, the following additional keys may be required: ACCESS_KEY: Requires user (access key) and api_key (access secret). EXTERNAL_ROLE: Requires roleArn and externalId. CONDUCTOR_ROLE: No additional keys required.	awsAccountId
gcp	projectName, environment, file	–
relational_db	jdbcDriver, user, password, datasourceURL	–
sendgrid	api_key	–
git	user, api_key	–

For example, if you are adding an Anthropic Claude integration, the configuration looks like this:

{
      "name": "<YOUR-INTEGRATION-NAME>",
      "type": "anthropic",
      "category": "AI_MODEL",
      "description": "<YOUR-DESCRIPTION>",
      "enabled": true,
      "configuration": {
        "api_key": "<YOUR-API-KEY>",
        "endpoint": "https://api.anthropic.com/v1"
      }
    }

Usage notes

Create: If no provider exists with the name, a new one is created and the caller is automatically granted full access.
Update: If a provider with the name already exists, it is updated.
Type immutability: The type field cannot be changed after the provider is created. Attempting to change it returns a 400 error.
Pinecone: For type: pineconedb, the projectName is auto-resolved from the Pinecone control plane. The api_key and environment fields are required in configuration.
OAuth2: If the provider has OAuth2 token fields and oAuth2AuthCode is present in configuration, the authorization code is exchanged for tokens automatically.
HuggingFace: Any model entries discovered in the configuration are automatically registered as integration models.
Secrets: Configuration keys of type PASSWORD are saved to the configured secrets backend (e.g., AWS Secrets Manager, Azure Key Vault) rather than stored in plain text.

Response

Status	Description
200 OK	Returns the created or updated integration provider object, including fields such as `name`, `type`, `category`, `description`, `enabled`, `configuration`, `tags`, `modelsCount`, `createTime`, `updateTime`, `createdBy`, and `updatedBy`.
400 Bad Request	Returns for an invalid input. For example, attempting to change the `type` of an existing integration.
403 Forbidden	Indicates that the authenticated user does not have permission to update one or more integrations.
404	The `type` is not a recognized integration on this server.

Examples

Create a new integration provider

The following request creates a new OpenAI integration provider.

Request

curl -X 'POST' \
  'https://<YOUR-SERVER-URL>/api/integrations/provider/openAI-marketing' \
  -H 'accept: */*' \
  -H 'X-Authorization: <TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "type": "openai",
  "category": "AI_MODEL",
  "description": "OpenAI account for the marketing team",
  "configuration": {
    "api_key": "sk-..."
  },
  "enabled": true
}'

Response

Returns 200 OK with the created integration provider object.

{
  "createTime": 1780923107007,
  "updateTime": 1780923120214,
  "createdBy": "john.doe@acme.com",
  "updatedBy": "john.doe@acme.com",
  "name": "openAI-eng",
  "type": "openai",
  "description": "OpenAI account for the marketing team",
  "category": "AI_MODEL",
  "configuration": {
    "api_key": "xxxxxxxxxx"
  },
  "enabled": true,
  "modelsCount": 0
}

Update an existing integration provider

The following request updates an existing OpenAI integration provider to disable it.