Google | Composio

Composio integrates with Google through Gemini function calling and the Agent Development Kit (ADK). Pick the tab that matches your integration.

The Google Generative AI provider transforms Composio tools into a format compatible with Gemini function calling.

Install

pip install composio composio_google google-genai

npm install @composio/core @composio/google @google/genai

Configure API Keys

Set COMPOSIO_API_KEY with your API key from Settings and GOOGLE_API_KEY with your Google API key.

.env

COMPOSIO_API_KEY=xxxxxxxxx
GOOGLE_API_KEY=xxxxxxxxx

Create session and run

from composio import Composio
from composio_google import GoogleProvider
from google import genai
from google.genai import types

composio = Composio(provider=GoogleProvider())
client = genai.Client()

# Create a session for your user
session = composio.create(user_id="user_123")
tools = session.tools()

config = types.GenerateContentConfig(tools=tools)
chat = client.chats.create(model="gemini-3-pro-preview", config=config)
response = chat.send_message("Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'")

# Agentic loop — keep executing tool calls until the model responds with text
while response.function_calls:
    parts = []
    for fc in response.function_calls:
        result = composio.provider.execute_tool_call(user_id="user_123", function_call=fc)
        parts.append(types.Part.from_function_response(name=fc.name, response=result))
    response = chat.send_message(parts)

print(response.text)

import { Composio } from '@composio/core';
import { GoogleProvider } from '@composio/google';
import { GoogleGenAI, type Part } from '@google/genai';

const composio = new Composio({
    provider: new GoogleProvider(),
});
const ai = new GoogleGenAI({ apiKey: process.env.GOOGLE_API_KEY! });

// Create a session for your user
const session = await composio.create("user_123");
const tools = await session.tools();

const chat = ai.chats.create({
    model: 'gemini-3-pro-preview',
    config: {
        tools: [{ functionDeclarations: tools }],
    },
});

let response = await chat.sendMessage({
    message: "Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'",
});

// Agentic loop — keep executing tool calls until the model responds with text
while (response.functionCalls && response.functionCalls.length > 0) {
    const parts: Part[] = [];
    for (const fc of response.functionCalls) {
        const result = await composio.provider.executeToolCall("user_123", {
            name: fc.name || '',
            args: (fc.args || {}) as Record<string, unknown>,
        });
        parts.push({
            functionResponse: {
                id: fc.id,
                name: fc.name,
                response: JSON.parse(result),
            },
        });
    }
    response = await chat.sendMessage({ message: parts });
}

console.log(response.text);

Edit this page on GitHub