# Google Gemini + Hugging Face — Pipedream Connect

> Connect a user's Google Gemini and Hugging Face accounts and expose tools for both apps directly in your product or your agent.

- Apps: Google Gemini (`google_gemini`) + Hugging Face (`hugging_face`)
- This page (HTML): https://pipedream.com/apps/google-gemini/integrations/hugging-face
- One `external_user_id` owns both connected accounts, and each account stays independently revocable.

## One session, both toolsets (recommended)

- Endpoint: `https://remote.mcp.pipedream.net/v3`
- Headers: `Authorization: Bearer <token>` · `x-pd-project-id` · `x-pd-environment` · `x-pd-external-user-id` · `x-pd-app-slug: google_gemini,hugging_face`
- `x-pd-app-slug` takes a comma-separated list, so `google_gemini,hugging_face` is one session on one transport. Both toolsets arrive from a single `listTools()`, and a tool is called exactly as it would be in a single-app session.

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
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 accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_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": "google_gemini,hugging_face",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// One list, both toolsets: Google Gemini and Hugging Face tools arrive
// together, each keyed by its own app's slug.

// e.g. run Generate Content from Text:
const result = await mcp.callTool({
  name: "google_gemini-generate-content-from-text",
  arguments: {
    model: "Model",
    text: "Prompt Text",
  },
})
```

Docs: [MCP guide](https://pipedream.com/docs/connect/mcp/developers.md)

## Both apps from your backend

```ts
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 externalUserId = "{external_user_id}" // any stable ID for this user in your system

const [googleGeminiTools, huggingFaceTools] =
  await Promise.all([
    pd.components.list({ app: "google_gemini" }),
    pd.components.list({ app: "hugging_face" }),
  ])

// One external user owns both connected accounts, so either app's tools
// run on their behalf with the same externalUserId.
```

Docs: [Managed auth guide](https://pipedream.com/docs/connect/managed-auth/quickstart.md) · [Tools guide](https://pipedream.com/docs/connect/components.md)

## Google Gemini

- API slug: `google_gemini` (use in MCP headers and tool keys)
- Auth: API key (Pipedream-managed)
- Categories: Artificial Intelligence (AI)
- Website: https://blog.google/technology/ai/google-gemini-pro-imagen-duet-ai-update/
- App page (HTML): https://pipedream.com/apps/google-gemini
- Tools: 3 actions · 0 triggers

Full tool list, API proxy, and SDK quickstart: https://pipedream.com/apps/google-gemini.md

### Actions (3)

- [Generate Content from Text](https://pipedream.com/apps/google-gemini/actions/generate-content-from-text.md) — `google_gemini-generate-content-from-text`
- [Generate Content from Text and Image](https://pipedream.com/apps/google-gemini/actions/generate-content-from-text-and-image.md) — `google_gemini-generate-content-from-text-and-image`
- [Generate Embeddings](https://pipedream.com/apps/google-gemini/actions/generate-embeddings.md) — `google_gemini-generate-embeddings`

## Hugging Face

- API slug: `hugging_face` (use in MCP headers and tool keys)
- Auth: API key (Pipedream-managed)
- Categories: Artificial Intelligence (AI)
- Website: https://huggingface.co/
- App page (HTML): https://pipedream.com/apps/hugging-face
- Tools: 6 actions · 0 triggers

Full tool list, API proxy, and SDK quickstart: https://pipedream.com/apps/hugging-face.md

### Actions (6)

- [Document Question Answering](https://pipedream.com/apps/hugging-face/actions/document-question-answering.md) — `hugging_face-document-question-answering`
- [Image Classification](https://pipedream.com/apps/hugging-face/actions/image-classification.md) — `hugging_face-image-classification`
- [Language Translation](https://pipedream.com/apps/hugging-face/actions/language-translation.md) — `hugging_face-language-translation`
- [Object Detection](https://pipedream.com/apps/hugging-face/actions/object-detection.md) — `hugging_face-object-detection`
- [Text Classification](https://pipedream.com/apps/hugging-face/actions/text-classification.md) — `hugging_face-text-classification`
- [Text Summarization](https://pipedream.com/apps/hugging-face/actions/text-summarization.md) — `hugging_face-text-summarization`

---

- Google Gemini: https://pipedream.com/apps/google-gemini.md · Hugging Face: https://pipedream.com/apps/hugging-face.md
- All apps: https://pipedream.com/apps — index: https://pipedream.com/llms.txt
- Pipedream docs for agents: https://pipedream.com/docs/llms.txt