CONNECT APP

Build with Google Gemini

Google Gemini is a multimodal AI by DeepMind that processes text, audio, images, and more.

Artificial Intelligence (AI)

API key

Visit Google Gemini ↗ Start building

MCP

Give your agent Google Gemini tools

Every Google Gemini 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 Google Gemini 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": "google_gemini",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// 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",
  },
})

# 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": "google_gemini",
}

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 Generate Content from Text:
        result = await session.call_tool("google_gemini-generate-content-from-text", {
            "model": "Model",
            "text": "Prompt Text",
        })

MCP guide →

API PROXY

Call the Google Gemini API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Google Gemini 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://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash",
})

// Any allowed Google Gemini 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://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9nZW5lcmF0aXZlbGFuZ3VhZ2UuZ29vZ2xlYXBpcy5jb20vdjFiZXRhL21vZGVscy9nZW1pbmktMS41LWZsYXNo?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 Google Gemini actions from your backend

Connect a user's Google Gemini account once, then run Generate Content from Text 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: "google_gemini-generate-content-from-text",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    google_gemini: { authProvisionId: "apn_xxxxxxx" },
    model: "Model",
    text: "Prompt Text",
  },
})

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="google_gemini-generate-content-from-text",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "google_gemini": {"authProvisionId": "apn_xxxxxxx"},
        "model": "Model",
        "text": "Prompt Text",
    },
)

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": "google_gemini-generate-content-from-text",
    "configured_props": {
      "google_gemini": { "authProvisionId": "apn_xxxxxxx" },
      "model": "Model",
      "text": "Prompt Text"
    }
  }'