MCP

Give your agent Hugging Face tools

Every Hugging Face 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 Hugging Face 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": "hugging_face",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Document Question Answering:
const result = await mcp.callTool({
  name: "hugging_face-document-question-answering",
  arguments: {
    modelId: "Model ID",
    imageUrl: "Image URL",
  },
})

# 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": "hugging_face",
}

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 Document Question Answering:
        result = await session.call_tool("hugging_face-document-question-answering", {
            "modelId": "Model ID",
            "imageUrl": "Image URL",
        })

MCP guide →

API PROXY

Call the Hugging Face API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Hugging Face 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://huggingface.co/api/whoami-v2",
})

// Any allowed Hugging Face 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://huggingface.co/api/whoami-v2

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9odWdnaW5nZmFjZS5jby9hcGkvd2hvYW1pLXYy?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 Hugging Face actions from your backend

Connect a user's Hugging Face account once, then run Document Question Answering 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: "hugging_face-document-question-answering",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    hugging_face: { authProvisionId: "apn_xxxxxxx" },
    modelId: "Model ID",
    imageUrl: "Image URL",
  },
})

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="hugging_face-document-question-answering",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "hugging_face": {"authProvisionId": "apn_xxxxxxx"},
        "modelId": "Model ID",
        "imageUrl": "Image URL",
    },
)

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": "hugging_face-document-question-answering",
    "configured_props": {
      "hugging_face": { "authProvisionId": "apn_xxxxxxx" },
      "modelId": "Model ID",
      "imageUrl": "Image URL"
    }
  }'