How to integrate Tally MCP with LangChain

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

30 min · no commitment · see it on your stack

Tally logo
LangChain logo
divider

Introduction

This guide walks you through connecting Tally to LangChain using the Composio tool router. By the end, you'll have a working Tally agent that can list all forms i created this month, download latest responses from your survey form, add a webhook to notify on new submission through natural language commands.

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

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

Also integrate Tally with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Tally project to Composio
  • Create a Tool Router MCP session for Tally
  • Initialize an MCP client and retrieve Tally tools
  • Build a LangChain agent that can interact with Tally
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

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

The Tally MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Tally account. It provides structured and secure access to your forms and response data, so your agent can perform actions like creating forms, retrieving responses, managing webhooks, and automating data collection workflows on your behalf.

  • Automated form creation and management: Have your agent create new forms, update existing ones, or delete forms as needed—no manual setup required.
  • Seamless response collection and analysis: Instantly fetch all responses to any form, enabling real-time data analysis, exports, or notifications.
  • Detailed form insights and field discovery: Retrieve comprehensive details about a form’s configuration, fields, and settings to power dynamic workflows or audits.
  • Webhook automation and event monitoring: Set up and manage webhooks to trigger custom actions when new responses come in, and review delivery history for full visibility.
  • User account and access checks: Let your agent fetch authenticated user info to confirm account status or permissions before performing sensitive operations.

Supported Tools & Triggers

Tools
Create FormTool to create a new form.
Create WebhookTool to create a new webhook for a form.
Delete FormTool to delete a specific form identified by its ID.
Delete WebhookTool to delete a specific webhook.
Get Form DetailsTool to retrieve details of a specific form.
Get Form ResponsesTool to retrieve the responses of a specific form.
Get User InfoTool to retrieve information about the authenticated user.
Get Webhook EventsTool to list events associated with a specific webhook.
Get WorkspaceTool to retrieve a single workspace by its ID with associated members.
List Form QuestionsTool to retrieve all questions from a specific form.
List FormsTool to retrieve a paginated list of forms.
List Organization InvitesTool to retrieve all pending invites in your organization.
List Organization UsersTool to retrieve all users in an organization.
List WebhooksTool to retrieve a paginated list of configured webhooks.
List WorkspacesTool to retrieve a paginated list of workspaces.
Update FormTool to update form details.
Update WebhookTool to update an existing webhook configuration.
Update WorkspaceTool to update the details of a specific workspace identified by its ID.

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 starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-langchain langchain-mcp-adapters langchain python-dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • composio-langchain provides Composio integration for LangChain
  • langchain-mcp-adapters enables MCP client connections
  • langchain is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Tally functionality through MCP

Initialize Composio client

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Tally tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

# Create Tool Router session for Tally
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['tally']
)

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Tally tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Tally tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "tally-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Tally MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Tally tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Tally related question or task to the agent.\n")

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ['exit', 'quit', 'bye']:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
What's happening:
  • We initialize an empty conversation_history list to maintain context across interactions
  • A while loop continuously accepts user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the ainvoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • We call the main() function using asyncio.run() to start the application

Complete Code

Here's the complete code to get you started with Tally and LangChain:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['tally']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "tally-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Tally related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've successfully built a LangChain agent that can interact with Tally through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Tally MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Tally MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Tally MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Tally MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Tally MCP with Claude Cowork

Codex logo

Codex

Use Tally MCP with Codex

OpenClaw logo

OpenClaw

Use Tally MCP with OpenClaw

Hermes logo

Hermes

Use Tally MCP with Hermes

CLI logo

CLI

Use Tally MCP with CLI

Google ADK logo

Google ADK

Use Tally MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Tally MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Tally MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Tally MCP with LlamaIndex

CrewAI logo

CrewAI

Use Tally MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with LangChain?

Yes, you can. LangChain 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 Tally tools.

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

Yes, absolutely. You can configure which Tally 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 Tally 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↗