SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Reply io MCP with Google ADK

Connect Google ADK to Reply io MCP. List all active campaigns this week, show contacts added to sales lists, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Reply io logoReply io
Api Key

Reply.io is an AI-powered sales engagement platform for automating sales outreach across multiple channels. Boosts lead conversion and sales productivity through integrated workflows.

35 Tools

Introduction

This guide walks you through connecting Reply io to Google ADK using the Composio tool router. By the end, you'll have a working Reply io agent that can create and update contacts, add contacts to sequences, start and pause sequences, track sequence stats, and connect email accounts through natural language commands.

This guide will help you understand how to give your Google ADK agent real control over a Reply io account through Composio's Reply io MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Reply io with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get a Reply io account set up and connected to Composio
  • Install the Google ADK and Composio packages
  • Create a Composio Tool Router session for Reply io
  • Build an agent that connects to Reply io through MCP
  • Interact with Reply io using natural language

What is Google ADK?

Google ADK (Agents Development Kit) is Google's framework for building AI agents powered by Gemini models. It provides tools for creating agents that can use external services through the Model Context Protocol.

Key features include:

  • Gemini Integration: Native support for Google's Gemini models
  • MCP Toolset: Built-in support for Model Context Protocol tools
  • Streamable HTTP: Connect to external services through streamable HTTP
  • CLI and Web UI: Run agents via command line or web interface

What is the Reply io MCP server, and what's possible with it?

The Reply io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Reply io account. It provides structured and secure access to your sales engagement platform, so your agent can manage campaigns, handle contacts, organize sequences, and automate routine sales operations on your behalf.

  • Campaign and sequence management: Effortlessly list, browse, and delete campaigns or sequences to keep your outreach organized and up to date.
  • Contact and list organization: Let your agent fetch, review, and organize your Reply io contacts and contact lists for targeted sales actions.
  • Email account administration: Retrieve all connected email accounts or remove outdated ones, making sure your sales tools stay streamlined.
  • User and access control: Easily remove users or generate unique identifiers for tasks, maintaining security and clarity in your team’s workflow.
  • Automated data retrieval: Quickly pull up paginated lists of campaigns, sequences, email accounts, or contact lists to inform your sales strategies and next steps.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • A Google API key for Gemini models
  • A Composio account and API key
  • Python 3.9 or later installed
  • Basic familiarity with Python
2

Getting API Keys for Google and Composio

Google API Key
  • Go to Google AI Studio and create an API key.
  • Copy the key and keep it safe. You will put this in GOOGLE_API_KEY.
Composio API Key and User ID
  • Log in to the Composio dashboard.
  • Go to Settings → API Keys and copy your Composio API key. Use this for COMPOSIO_API_KEY.
  • Decide on a stable user identifier to scope sessions, often your email or a user ID. Use this for COMPOSIO_USER_ID.
3

Install dependencies

bash
pip install google-adk composio python-dotenv

Inside your virtual environment, install the required packages.

What's happening:

  • google-adk is Google's Agents Development Kit
  • composio connects your agent to Reply io via MCP
  • python-dotenv loads environment variables
4

Set up ADK project

bash
adk create my_agent

Set up a new Google ADK project.

What's happening:

  • This creates an agent folder with a root agent file and .env file
5

Set environment variables

bash
GOOGLE_API_KEY=your-google-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id-or-email

Save all your credentials in the .env file.

What's happening:

  • GOOGLE_API_KEY authenticates with Google's Gemini models
  • COMPOSIO_API_KEY authenticates with Composio
  • COMPOSIO_USER_ID identifies the user for session management
6

Import modules and validate environment

python
import os
import warnings

from composio import Composio
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()

warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")
What's happening:
  • os reads environment variables
  • Composio is the main Composio SDK client
  • GoogleProvider declares that you are using Google ADK as the agent runtime
  • Agent is the Google ADK LLM agent class
  • McpToolset lets the ADK agent call MCP tools over HTTP
7

Create Composio client and Tool Router session

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["reply_io"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url,
print(f"Composio MCP URL: {COMPOSIO_MCP_URL}")
What's happening:
  • Authenticates to Composio with your API key
  • Declares Google ADK as the provider
  • Spins up a short-lived MCP endpoint for your user and selected toolkit
  • Stores the MCP HTTP URL for the ADK MCP integration
8

Set up the McpToolset and create the Agent

python
composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Reply io operations."
    ),
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")
What's happening:
  • Connects the ADK agent to the Composio MCP endpoint through McpToolset
  • Uses Gemini as the model powering the agent
  • Lists exact tool names in instruction to reduce misnamed tool calls
9

Run the agent

bash
# Run in CLI mode
adk run my_agent

# Or run in web UI mode
adk web

Execute the agent from the project root. The web command opens a web portal where you can chat with the agent.

What's happening:

  • adk run runs the agent in CLI mode
  • adk web . opens a web UI for interactive testing

Complete Code

Here's the complete code to get you started with Reply io and Google ADK:

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()
warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["reply_io"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url


composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Reply io operations."
    ),  
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")

Conclusion

You've successfully integrated Reply io with the Google ADK through Composio's MCP Tool Router. Your agent can now interact with Reply io using natural language commands.

Key takeaways:

  • The Tool Router approach dynamically routes requests to the appropriate Reply io tools
  • Environment variables keep your credentials secure and separate from code
  • Clear agent instructions reduce tool calling errors
  • The ADK web UI provides an interactive interface for testing and development

You can extend this setup by adding more toolkits to the toolkits array in your session configuration.

TOOLS

Supported Tools

Every Reply io action and event your agent gets out of the box.

Add Contact to Sequence

Move an existing contact to a sequence in Reply.

Archive Sequence

Tool to archive a sequence.

Clear Contact Status

Tool to clear statuses from contacts.

Connect Exchange Account via OAuth

Tool to initiate OAuth connection for an Exchange email account.

Connect Gmail Account

Tool to initiate Gmail account connection via OAuth.

Create Contact

Tool to create a new contact in Reply.

Create Sequence Step

Add a step to an existing Reply.

Delete Contact

Delete a contact by ID.

Delete Email Account

Delete an email account by ID.

Delete Schedule

Delete a schedule by ID using the Reply API v2.

Delete Sequence

Tool to delete a sequence.

Delete User

Requests deletion of a user by ID.

Generate ULID

Generate a ULID-like identifier using a millisecond timestamp and a random alphanumeric suffix.

Get Contact Activities

Retrieve one page of tracked activities for a Reply.

Get Contact by ID

Tool to retrieve a contact by ID.

Get Contact Status

Tool to get contact status.

Get Current User

Tool to get the current authenticated user's ID.

Reply.io Get Disconnected Email Accounts

List disconnected email accounts for troubleshooting.

Get Sequence By ID

Tool to retrieve detailed information about a sequence by its ID.

Get Sequence Contacts Extended

Retrieve a page of contacts enrolled in a sequence, with optional additional details such as engagement status, current step and completion timestamps.

Get Sequence Stats

Get aggregate email and LinkedIn engagement statistics for a sequence.

Get Sequence Step by ID

Tool to retrieve details of a specific sequence step.

List Contacts Basic

List contacts to gather contact IDs, with page and page-size controls.

Reply.io List Email Accounts

List Reply.

Reply.io List Lists

List contact lists in the Reply.

List Sequences

Browse Reply.

List Sequence Steps

Tool to retrieve all steps in a sequence.

Pause Sequence

Tool to pause a running sequence.

Remove Contact From Sequence

Tool to remove a contact from a sequence.

Bulk Remove Contacts from Sequence

Tool to bulk remove multiple contacts from a sequence at once.

Search Contacts by Email

Search Reply.

Set Contact Status

Tool to set the status of one or more contacts.

Start Sequence

Tool to start a sequence.

Update Contact

Tool to update an existing contact's information.

Update Email Account

Update an email account's custom SMTP/IMAP configuration, sender name, signature and daily limit.

FRAMEWORKS

How to build Reply io MCP Agent with another framework

Claude Code logo

Claude Code

Use Reply io MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Reply io MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Reply io MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Reply io MCP with Claude Agent SDK

Codex logo

Codex

Use Reply io MCP with Codex

OpenClaw logo

OpenClaw

Use Reply io MCP with OpenClaw

Hermes logo

Hermes

Use Reply io MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Reply io MCP with Atomic Agent

LangChain logo

LangChain

Use Reply io MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Reply io MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Reply io MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Reply io MCP with LlamaIndex

CrewAI logo

CrewAI

Use Reply io MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Reply io MCP with Pydantic AI

AutoGen logo

AutoGen

Use Reply io MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Reply io MCP server, the agents and LLMs can only access a fixed set of Reply io tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Reply io and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Google ADK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Reply io tools.

Yes, absolutely. You can configure which Reply io scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Reply io data and credentials are handled as safely as possible.

Start with Reply io.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Reply io tool your agent needs.Free to start.

Start building