CONNECT APP

Build with Azure OpenAI

Apply large language models and generative AI to a variety of use cases

Artificial Intelligence (AI)

API key

Visit Azure OpenAI ↗ Start building

MCP

Give your agent Azure OpenAI tools

Every Azure OpenAI action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Azure OpenAI account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "azure_openai_service",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Chat:
const result = await mcp.callTool({
  name: "azure_openai_service-chat",
  arguments: {
    userMessage: "User Message",
    systemInstructions: "System Instructions",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "azure_openai_service",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Chat:
        result = await session.call_tool("azure_openai_service-chat", {
            "userMessage": "User Message",
            "systemInstructions": "System Instructions",
        })

MCP guide →

API PROXY

Call the Azure OpenAI API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Azure OpenAI API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.example.com/v1/me",
})

// Any allowed Azure OpenAI endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.example.com/v1/me

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuZXhhbXBsZS5jb20vdjEvbWU?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run Azure OpenAI actions from your backend

Connect a user's Azure OpenAI account once, then run Chat on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "azure_openai_service-chat",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    azure_openai_service: { authProvisionId: "apn_xxxxxxx" },
    userMessage: "User Message",
    systemInstructions: "System Instructions",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="azure_openai_service-chat",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "azure_openai_service": {"authProvisionId": "apn_xxxxxxx"},
        "userMessage": "User Message",
        "systemInstructions": "System Instructions",
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "azure_openai_service-chat",
    "configured_props": {
      "azure_openai_service": { "authProvisionId": "apn_xxxxxxx" },
      "userMessage": "User Message",
      "systemInstructions": "System Instructions"
    }
  }'