How to integrate Handwrytten MCP with LlamaIndex

GET STARTED FOR FREE
Framework Integration Gradient
Handwrytten Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Handwrytten to LlamaIndex using the Composio tool router. By the end, you'll have a working Handwrytten agent that can send a thank you card to john doe, schedule a handwritten birthday note delivery, list all pending handwrytten orders through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Handwrytten account through Composio's Handwrytten 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 Handwrytten
  • Connect LlamaIndex to the Handwrytten MCP server
  • Build a Handwrytten-powered agent using LlamaIndex
  • Interact with Handwrytten 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 Handwrytten MCP server, and what's possible with it?

The Handwrytten MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Handwrytten account. It provides structured and secure access so your agent can perform Handwrytten operations on your behalf.

Supported Tools & Triggers

Tools
Add RecipientTool to add a recipient address to the user's addressbook in Handwrytten.
Calculate Order TaxesTool to calculate taxes for Handwrytten basket orders.
Check AuthenticationTool to verify API key authentication validity for Handwrytten.
Clear BasketTool to clear all items from the shopping basket.
Create TemplateTool to create a new template for the current user.
Create User AddressTool to create a new user address in Handwrytten.
Delete Custom ImageTool to delete a custom image/logo from Handwrytten.
Delete Recipient AddressTool to delete one or more recipient addresses from user's profile.
Delete TemplateTool to delete a user's template by its ID.
Get Basket (New Method)Tool to retrieve the user's basket using the new method.
Get Basket CountTool to retrieve the count of items currently in the basket.
Get Basket ItemTool to retrieve a basket item by its ID from Handwrytten.
Get Card DetailsTool to get detailed information about a specific card in the Handwrytten catalog.
Get List of AddressesTool to retrieve a list of all addresses associated with the user's account.
Get Random CardsTool to retrieve random cards from Handwrytten.
Get Template DetailsTool to get detailed information about a card text template in the Handwrytten catalog.
Get Current User InfoTool to retrieve information about the currently authenticated user.
Get User AddressTool to retrieve the authenticated user's address and billing information.
List Basket Orders GroupedTool to list all basket orders grouped by basket.
List Past BasketsTool to retrieve a list of user's past baskets.
List CardsTool to retrieve a list of available Handwrytten cards with optional filtering and pagination.
List CategoriesTool to retrieve the list of available card categories from Handwrytten.
List CountriesTool to retrieve the list of countries available in Handwrytten.
List Credit CardsTool to list all credit cards associated with the Handwrytten account.
List FontsTool to retrieve the list of available handwriting fonts.
List Fonts for CustomizerTool to list fonts available for use with the card customizer.
List Gift CardsTool to retrieve the list of available gift cards with their denominations and pricing.
List Custom User ImagesTool to retrieve a list of custom user images uploaded to Handwrytten.
List InsertsTool to retrieve a list of available inserts from Handwrytten.
List OrdersTool to retrieve a list of user's past orders from Handwrytten.
List Orders GroupedTool to retrieve the user's order history grouped by basket.
List Past OrdersTool to retrieve a list of user's past orders from Handwrytten API.
List RecipientsTool to retrieve a list of recipient addresses that the user has previously saved.
List SignaturesTool to retrieve the list of available signatures for use in card orders.
List StatesTool to retrieve the list of states/provinces available in Handwrytten.
List Template CategoriesTool to retrieve the list of available template categories from Handwrytten.
List TemplatesTool to retrieve a list of card text templates from Handwrytten.
Logout UserTool to logout user from Handwrytten application.
Place Order in BasketTool to add an order to the basket in Handwrytten.
Register UserTool to register a new Handwrytten user account.
Request Password ResetTool to request a password reset email for a Handwrytten account.
Set Default AddressTool to set a default return address for the user in Handwrytten.
Set Test ModeTool to set test mode for the current Handwrytten user.
Update Basket ItemTool to update an existing basket item in Handwrytten.
Update Billing InformationTool to update user billing information (country, zip, address) for tax calculations in Handwrytten.
Update RecipientTool to update a recipient address in the user's addressbook in Handwrytten.
Update TemplateTool to update an existing user template in Handwrytten.
Upload Custom LogoTool to upload a custom image (logo or cover) to Handwrytten for use with custom cards.

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 Handwrytten account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Handwrytten

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 Handwrytten 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 handwrytten_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=["handwrytten"],
    )

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

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Handwrytten 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=["handwrytten"],
    )

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Handwrytten MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Handwrytten MCP with Claude Agent SDK

Google ADK

Google ADK

Use Handwrytten MCP with Google ADK

LangChain

LangChain

Use Handwrytten MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Handwrytten MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Handwrytten MCP with Mastra AI

CrewAI

CrewAI

Use Handwrytten MCP with CrewAI

Claude Code

Claude Code

Use Handwrytten MCP with Claude Code

Codex

Codex

Use Handwrytten MCP with Codex

FAQ

What are the differences in Tool Router MCP and Handwrytten MCP?

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

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

Yes, absolutely. You can configure which Handwrytten 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 Handwrytten 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