How to integrate Zoho bigin MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Zoho bigin logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Zoho bigin to LlamaIndex using the Composio tool router. By the end, you'll have a working Zoho bigin agent that can add new contact to sales pipeline, list all open deals this week, tag recent leads as 'hot prospects' through natural language commands.

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

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

Also integrate Zoho bigin with

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 Zoho bigin
  • Connect LlamaIndex to the Zoho bigin MCP server
  • Build a Zoho bigin-powered agent using LlamaIndex
  • Interact with Zoho bigin 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 Zoho bigin MCP server, and what's possible with it?

The Zoho bigin MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoho bigin account. It provides structured and secure access to your CRM pipeline data, so your agent can manage contacts, track deals, organize records, handle attachments, and streamline your small business workflows—all on your behalf.

  • Automated record management: Add, update, or delete records in any Zoho bigin module to keep your CRM data accurate and up to date.
  • Tagging and categorization: Create new tags or apply them to records, making it easy to segment contacts, deals, or companies for better organization.
  • Attachment handling: Retrieve, download, or delete attachments associated with your records, letting your agent manage files and documents with ease.
  • Module and data discovery: List available modules and fetch records with sorting, filtering, and pagination—perfect for quickly surfacing the data you need.
  • Deleted records auditing: Access and review recently deleted records for auditing or restoration, helping you maintain data integrity and recover lost information.

Supported Tools & Triggers

Tools
Add RecordsTool to add new records to a module.
Add Tags to RecordsTool to add tags to a specific record in a module.
Create Bulk Read JobTool to create a bulk read job for exporting large amounts of data asynchronously.
Create NotesTool to create notes and associate them with records in Zoho Bigin.
Create Record NotesTool to create new notes for a specific record.
Create TagsTool to create tags for a module.
Delete AttachmentTool to delete an attachment from a record.
Delete NoteTool to delete a note from a specific record.
Delete NotesTool to delete multiple notes from Zoho Bigin.
Delete RecordTool to delete a specific record from a module.
Delete Record PhotoTool to delete a profile photo from a record.
Delete RecordsTool to delete records from a module.
Delink Related RecordsTool to delete the association between a module record and related list records.
Disable NotificationsTool to disable instant notifications for one or more channels.
Download AttachmentTool to download an attachment from a record.
Download Bulk Read ResultTool to download the bulk read job result in ZIP format (containing CSV or ICS export).
Download Record PhotoTool to download the profile photo associated with a specific record.
Enable NotificationsTool to enable instant webhook notifications for module events in Bigin.
Get All NotesTool to retrieve the list of notes associated with records.
Get AttachmentsTool to retrieve attachments for a record.
Get Bulk Read Job StatusTool to retrieve the details of a bulk read job performed earlier.
Get Custom ViewTool to get the metadata of a specific custom view configured in a module.
Get Custom ViewsTool to retrieve the list of custom views available for a module.
Get Deleted RecordsTool to get a list of deleted records in a module.
Get FieldsTool to retrieve field metadata for a Bigin module.
Get LayoutTool to retrieve details of a specific layout by layout ID.
Get LayoutsTool to retrieve the list of layouts available for a module.
Get Module MetadataTool to retrieve metadata of a specific module by its API name.
Get ModulesTool to retrieve a list of all modules.
Get Notification DetailsTool to retrieve information about enabled notifications.
Get OrganizationTool to retrieve organization details including name, ID, currency, time zone, and other settings.
Get ProfilesTool to retrieve the list of available profiles and their properties in an organization.
Get RecordTool to retrieve details of a specific record in a module using the record ID.
Get Record NotesTool to retrieve the list of notes associated with a specific record.
Get RecordsTool to retrieve records from a Bigin module.
Get Records CountTool to get the count of records in a Bigin module.
Get Related Lists MetadataTool to retrieve the list of related lists metadata for a module.
Get Related RecordsTool to retrieve related records associated with a specific record in a module.
Get RolesTool to retrieve the list of available roles and their properties in an organization.
Get Team Pipeline RecordsTool to retrieve pipeline records from Team Pipelines in Zoho Bigin.
Get UserTool to retrieve details of a specific user using the user identification.
Get UsersTool to retrieve the list of users in the organization.
Search RecordsTool to search for records in a Bigin module using various criteria.
Update NoteTool to update an existing note for a specific record in a module.
Update Notification DetailsTool to update notification channel details in Zoho Bigin.
Update Notification InfoTool to update specific notification information without losing existing data.
Update RecordsTool to update existing records in a module.
Update Related RecordsTool to update related records associated with a specific record in a module.
Update UserTool to update details of an existing user by user ID.
Update UsersTool to update details of multiple users in an organization.
Upload AttachmentTool to upload an attachment to a record.
Upload Organization PhotoTool to upload or update the brand logo or image for the current organization.
Upload Record PhotoTool to upload a photo/image to a specific record (e.
Upsert RecordsTool to insert or update records in a module based on unique field values.

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

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 Zoho bigin account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Zoho bigin

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 Zoho bigin 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 zoho bigin_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=["zoho_bigin"],
    )

    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 Zoho bigin actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Zoho bigin 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, zoho bigin)
  • 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 Zoho bigin 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 Zoho bigin 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 Zoho bigin

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Zoho bigin, then start asking questions.

Complete Code

Here's the complete code to get you started with Zoho bigin 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=["zoho_bigin"],
    )

    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 Zoho bigin actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Zoho bigin 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 Zoho bigin to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Zoho bigin 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 Zoho bigin MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Zoho bigin MCP with ChatGPT

Antigravity logo

Antigravity

Use Zoho bigin MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Zoho bigin MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Zoho bigin MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Zoho bigin MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Zoho bigin MCP with Claude Cowork

Codex logo

Codex

Use Zoho bigin MCP with Codex

OpenClaw logo

OpenClaw

Use Zoho bigin MCP with OpenClaw

Hermes logo

Hermes

Use Zoho bigin MCP with Hermes

CLI logo

CLI

Use Zoho bigin MCP with CLI

Google ADK logo

Google ADK

Use Zoho bigin MCP with Google ADK

LangChain logo

LangChain

Use Zoho bigin MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Zoho bigin MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Zoho bigin MCP with Mastra AI

CrewAI logo

CrewAI

Use Zoho bigin MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Zoho bigin MCP?

With a standalone Zoho bigin MCP server, the agents and LLMs can only access a fixed set of Zoho bigin tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Zoho bigin 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 Zoho bigin tools.

Can I manage the permissions and scopes for Zoho bigin while using Tool Router?

Yes, absolutely. You can configure which Zoho bigin 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 Zoho bigin 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.

Get started for freeGet a demo↗