How to integrate Benchmark email MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Benchmark email Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Benchmark email to LlamaIndex using the Composio tool router. By the end, you'll have a working Benchmark email agent that can list all confirmed sender email addresses, get my benchmark account plan details, fetch company profile and contact limits, retrieve all current account settings through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Benchmark email account through Composio's Benchmark email MCP server.

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

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Benchmark email
  • Connect LlamaIndex to the Benchmark email MCP server
  • Build a Benchmark email-powered agent using LlamaIndex
  • Interact with Benchmark email through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

What is the Benchmark email MCP server, and what's possible with it?

The Benchmark email MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Benchmark Email account. It provides structured and secure access to your email marketing data, so your agent can retrieve account info, manage contacts, handle lists, and automate campaign administration on your behalf.

  • Automated contact and list management: Effortlessly add, update, or delete contacts and lists, keeping your subscriber base organized and up to date.
  • Campaign cleanup and maintenance: Direct your agent to delete obsolete email campaigns or remove unneeded webhooks to keep your workspace tidy.
  • Account insights and configuration retrieval: Have the agent fetch client details, plan information, and account settings—perfect for reporting or reviewing your workspace setup.
  • Confirmed email address retrieval: Quickly pull all verified sender email addresses for compliance and seamless campaign sending.
  • Agency account and webhook control: Manage linked agency accounts and webhooks by deleting or updating them when no longer needed for more secure integrations.

Supported Tools & Triggers

Tools
Delete Contact From ListTool to delete a contact from a specific list by contactid.
Delete Contact ListTool to delete a contact list.
Delete Email CampaignTool to delete an email campaign.
Delete Linked Agency AccountTool to delete a linked agency account.
Delete WebhookTool to delete a webhook from a contact list by its id.
Get All Confirmed EmailsTool to retrieve all confirmed email addresses for the client account.
Get Client Account SettingsTool to get client account settings such as company, language, timezone, and sender info.
Get client detailsTool to get client details including profile data, contact count, and plan information.
Get Client Plan InformationTool to get client's plan information including addons, email plan, and total contacts.
Get client profile detailsTool to get client's profile details like business city, country, phone, and company.
Get Contact List DetailsTool to fetch detailed information for a contact list.
Get Contact ListsTool to retrieve all contact lists.
Get Filtered Contacts in ListTool to fetch filtered and paginated contacts from a list by listid.
Get Email Report ForwardsTool to get forwards report for an email campaign.
Get Unopens ReportTool to get unopens report for an email campaign by id.
Get Linked Agency Account DetailsTool to get details of a linked agency account.
Get Linked Agency AccountsTool to get list of linked agency accounts.
Get sub-account detailsTool to get details for a specific sub-account by id.
Get Sub-Account HistoryTool to get sub-account history.
Get Sub-AccountsTool to retrieve all sub-accounts for the client.
Get Sub-Accounts Plan ListTool to retrieve available plans for a sub-account.
Change PasswordTool to change the password for the client account.
Save Security PINTool to save a new security pin for the client account.
Send Reset EmailTool to send a reset email link to change the primary email address.
Patch Update Client SettingsTool to update client account settings.
Update Contact ListTool to update an existing contact list.
Update/Edit ProfileTool to update or edit profile information such as first name, last name, and phone number.
Update WebhookTool to update a webhook for a contact list by webhook id.
Add Contact to ListTool to add a new contact to a specific list.
Change Security PINTool to change security pin for the client account.
Create Contact ListTool to create a new contact list.
Create WebhookTool to create a new webhook for a contact list.
Disable Security PINTool to disable security pin for the client account.
Save Website DomainTool to save a website domain for your benchmark email account.
Send Confirm Email VerificationTool to send confirm email verification.
Send PIN via EmailTool to send pin via email.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Benchmark email account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Benchmark email

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Benchmark email access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called benchmark email_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

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

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_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:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["benchmark_email"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Benchmark email actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Benchmark email actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, benchmark email)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Benchmark email tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Benchmark email database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Benchmark email

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Benchmark email, then start asking questions.

Complete Code

Here's the complete code to get you started with Benchmark email and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

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

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["benchmark_email"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Benchmark email actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Benchmark email actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Benchmark email to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Benchmark email tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Benchmark email MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Benchmark email MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Benchmark email MCP with Claude Agent SDK

Google ADK

Google ADK

Use Benchmark email MCP with Google ADK

LangChain

LangChain

Use Benchmark email MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Benchmark email MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Benchmark email MCP with Mastra AI

CrewAI

CrewAI

Use Benchmark email MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Benchmark email MCP?

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Benchmark email tools.

Can I manage the permissions and scopes for Benchmark email while using Tool Router?

Yes, absolutely. You can configure which Benchmark email 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.

How safe is my data with Composio Tool Router?

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 Benchmark email data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free