CONNECT APP

Build with WatsonX AI

The AI and data platform that’s built for business-

Artificial Intelligence (AI)

OAuth

Visit WatsonX AI ↗ Start building

MCP

Give your agent WatsonX AI tools

Every WatsonX AI 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 WatsonX AI 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": "watsonx_ai",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()
// Every tool arrives with its own input schema — run one with mcp.callTool().

# 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": "watsonx_ai",
}

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()
        # Every tool arrives with its own input schema — run one with call_tool().

MCP guide →

API PROXY

Call the WatsonX AI API directly

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

Connect a user's WatsonX AI account once, then discover and run its tools 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 tools = await pd.components.list({
  app: "watsonx_ai",
  componentType: "action",
})

from pipedream import Pipedream

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

tools = pd.components.list(
    app="watsonx_ai",
    component_type="action",
)

curl "https://api.pipedream.com/v1/connect/{project_id}/components?app=watsonx_ai&component_type=action" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}"

Managed auth guide → Tools guide →

TOOLS