CONNECT APP

Build with Azure AI Vision

Azure AI Vision is a unified service that offers innovative computer vision capabilities. Give your apps the ability to analyze images, read text, and detect faces with prebuilt image tagging, text extraction with optical character recognition (OCR), and responsible facial recognition. Incorporate vision features into your projects with no machine learning experience required.

Artificial Intelligence (AI)

API key

Visit Azure AI Vision ↗ Start building

MCP

Give your agent Azure AI Vision tools

Every Azure AI Vision 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 AI Vision 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_ai_vision",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Extract Text from Image:
const result = await mcp.callTool({
  name: "azure_ai_vision-extract-text-from-image",
  arguments: {
    image: "Image URL",
    language: "Language",
  },
})

# 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_ai_vision",
}

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 Extract Text from Image:
        result = await session.call_tool("azure_ai_vision-extract-text-from-image", {
            "image": "Image URL",
            "language": "Language",
        })

MCP guide →

API PROXY

Call the Azure AI Vision API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Azure AI Vision 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 AI Vision 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 AI Vision actions from your backend

Connect a user's Azure AI Vision account once, then run Extract Text from Image 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_ai_vision-extract-text-from-image",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    azure_ai_vision: { authProvisionId: "apn_xxxxxxx" },
    image: "Image URL",
    language: "Language",
  },
})

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_ai_vision-extract-text-from-image",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "azure_ai_vision": {"authProvisionId": "apn_xxxxxxx"},
        "image": "Image URL",
        "language": "Language",
    },
)

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_ai_vision-extract-text-from-image",
    "configured_props": {
      "azure_ai_vision": { "authProvisionId": "apn_xxxxxxx" },
      "image": "Image URL",
      "language": "Language"
    }
  }'