SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Pandadoc MCP with LangChain

Connect LangChain to Pandadoc MCP. Create a new contract from pdf upload, add an attachment to a draft proposal, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Pandadoc logoPandadoc
Api Key

Pandadoc is a document automation platform for creating, sending, and e-signing proposals and contracts. It streamlines sales workflows and speeds up agreement processes.

111 Tools

Introduction

This guide walks you through connecting Pandadoc to LangChain using the Composio tool router. By the end, you'll have a working Pandadoc agent that can create documents from file uploads, manage templates, organize folders, update contacts, and search catalog items through natural language commands.

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

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

Also integrate Pandadoc with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Pandadoc project to Composio
  • Create a Tool Router MCP session for Pandadoc
  • Initialize an MCP client and retrieve Pandadoc tools
  • Build a LangChain agent that can interact with Pandadoc
  • 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 Pandadoc MCP server, and what's possible with it?

The Pandadoc MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pandadoc account. It provides structured and secure access to your documents, templates, contacts, and workflows, so your agent can perform actions like creating documents, managing templates, organizing folders, and handling contacts on your behalf.

  • Automated document creation and uploads: Have your agent generate new contracts, proposals, or agreements by uploading files or leveraging templates—ready for processing and e-signature in Pandadoc.
  • Template management and customization: Let your agent create, update, or delete templates, making it easy to standardize and scale your document workflows across teams.
  • Contact creation and maintenance: Seamlessly add, update, or delete contacts in your Pandadoc account, ensuring your address book stays organized and always up to date.
  • Folder and document organization: Ask your agent to create structured folders, move documents, or attach supplemental files to keep your workspace tidy and accessible.
  • Webhook setup for workflow automation: Empower your agent to create Pandadoc webhooks, so you can receive instant notifications about document status changes, completions, or updates—no manual checking required.

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 step10 STEPS
1

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
2

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.
3

Install dependencies

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters 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/core is the core agent framework
  • dotenv/config loads environment variables
4

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
5

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv/config import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Pandadoc functionality through MCP
6

Initialize Composio client

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
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 Pandadoc tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding
7

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['pandadoc']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Pandadoc 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 Pandadoc tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "pandadoc-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Pandadoc MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Pandadoc tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model
9

Set up interactive chat interface

let conversationHistory: any[] = [];

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

const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
});

rl.prompt();

rl.on('line', async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

    if (!trimmedInput) {
        rl.prompt();
        return;
    }

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
What's happening:
  • We initialize an empty conversationHistory list to maintain context across interactions
  • A readline interface is used to continuously accept 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 invoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully
10

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
What's happening:
  • We call the main() function to start the application

Complete Code

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

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['pandadoc']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "pandadoc-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Pandadoc related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\nSession ended.');
        process.exit(0);
    });
}

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});

Conclusion

You've successfully built a LangChain agent that can interact with Pandadoc 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.
TOOLS

Supported Tools

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

Add a document recipient

Add a document recipient.

Add a workspace member

Add a workspace member.

Append a content library item to a document

Append a content library item to a document.

Bulk-delete documents

Bulk-delete documents.

Change document ownership

Change document ownership.

Change document status

Change document status.

Change Document Status with Upload

Manually change a document's status with an optional file attachment.

Change a workspace member role

Change a workspace member role.

Create a content library item

Create a content library item.

Create Content Library Item from File Upload

Upload a file to create a PandaDoc content library item asynchronously.

Create Document Attachment

Creates and adds an attachment to a PandaDoc document.

Create a document editing session

Create a document editing session.

Create document fields

Create document fields.

Create Document from File Upload

Creates a new document in PandaDoc by uploading a file (PDF, DOCX, or RTF).

Create a document section

Create a document section.

Create Document Section from File Upload

Add a section to an existing version 2 document from a PDF, DOCX, or RTF.

Create an embedded signing session

Create an embedded signing session.

Create Document Folder

Creates a new folder in PandaDoc to organize documents.

Create a linked object

Create a linked object.

Create a notarization request

Create a notarization request.

Create or Update Contact

Create a PandaDoc contact or attempt to update an existing contact by email.

Create a product catalog item

Create a product catalog item.

Create Template

This tool allows users to create a new template in PandaDoc from a PDF file or from scratch.

Create a template editing session

Create a template editing session.

Create a template folder

Create a template folder.

Create a user

Create a user.

Create PandaDoc Webhook

Creates a new webhook subscription in PandaDoc to receive notifications about specific events.

Create a workspace

Create a workspace.

Deactivate a workspace

Deactivate a workspace.

Delete Contact

This tool allows you to delete a contact from your PandaDoc account.

Delete a document

Delete a document.

Delete a document attachment

Delete a document attachment.

Delete a document recipient

Delete a document recipient.

Delete a document section

Delete a document section.

Delete a linked object

Delete a linked object.

Delete a notarization request

Delete a notarization request.

Delete a product catalog item

Delete a product catalog item.

Delete Template

This tool deletes a specific template from PandaDoc.

Delete a webhook subscription

Delete a webhook subscription.

Download a completed document

Download a completed document.

Download Document

Download a PandaDoc document as PDF, or a bundle as separate PDFs in a ZIP.

Download a document attachment

Download a document attachment.

Duplicate a template

Duplicate a template.

Get API log details

Get API log details.

Get attachment details

Get attachment details.

Get automatic reminder settings

Get automatic reminder settings.

Get automatic reminder status

Get automatic reminder status.

Get contact details

Get contact details.

Get content library item details

Get content library item details.

Get content library item status

Get content library item status.

Get the current member

Get the current member.

Get Document Details

Fetch detailed metadata for a specific PandaDoc document including recipients, fields/tokens values, pricing data, metadata, tags, and content-block names.

Get the document eSign disclosure

Get the document eSign disclosure.

Get document section details

Get document section details.

Get document settings

Get document settings.

Get document status

Get document status.

Get member details

Get member details.

Get notarization request details

Get notarization request details.

Get a product catalog item

Get a product catalog item.

Get section upload status

Get section upload status.

Get Template Details

Retrieve details for a specific PandaDoc template by ID, including metadata, roles, fields, tokens and pricing information when available.

Get template settings

Get template settings.

Get template sharing settings

Get template sharing settings.

Get template status

Get template status.

Get a user by ID

Get a user by ID.

Get webhook event details

Get webhook event details.

Get webhook subscription details

Get webhook subscription details.

List API logs

List API logs.

List Contacts

List PandaDoc workspace contacts, optionally filtering by email address.

List content library items

List content library items.

List document attachments

List document attachments.

List document audit trail

List document audit trail.

List document fields

List document fields.

List Document Folders

List PandaDoc document folders, optionally specifying a parent folder and pagination.

List Documents

List and search PandaDoc documents with filters, pagination, and ordering.

List documents by linked object

List documents by linked object.

List document sections

List document sections.

List forms

List forms.

List linked objects

List linked objects.

List notaries

List notaries.

List notarization requests

List notarization requests.

List recent SMS opt-outs

List recent SMS opt-outs.

List template folders

List template folders.

List Templates

This tool retrieves a list of all templates available in the PandaDoc account.

List users

List users.

List webhook events

List webhook events.

List webhook subscriptions

List webhook subscriptions.

List workspace members

List workspace members.

List workspaces

List workspaces.

Move a document to draft

Move a document to draft.

Move Document to Folder

This tool allows users to move a document to a specific folder within their PandaDoc account.

Reassign a document signer

Reassign a document signer.

Remove a workspace member

Remove a workspace member.

Rename a document folder

Rename a document folder.

Rename a template folder

Rename a template folder.

Search Catalog Items

Search PandaDoc product catalog items with filters and ordering.

Search product catalog items

Search product catalog items.

Send a document

Send a document.

Send a manual reminder

Send a manual reminder.

Transfer ownership of all documents

Transfer ownership of all documents.

Update automatic reminder settings

Update automatic reminder settings.

Update a document

Update a document.

Update document field assignments

Update document field assignments.

Update a document quote

Update a document quote.

Update a document recipient

Update a document recipient.

Update document settings

Update document settings.

Update a product catalog item

Update a product catalog item.

Update a template

Update a template.

Update template settings

Update template settings.

Update template sharing settings

Update template sharing settings.

Update a webhook subscription

Update a webhook subscription.

FRAMEWORKS

How to build Pandadoc MCP Agent with another framework

Claude Code logo

Claude Code

Use Pandadoc MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Pandadoc MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Pandadoc MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Pandadoc MCP with Claude Agent SDK

Codex logo

Codex

Use Pandadoc MCP with Codex

OpenClaw logo

OpenClaw

Use Pandadoc MCP with OpenClaw

Hermes logo

Hermes

Use Pandadoc MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Pandadoc MCP with Atomic Agent

Google ADK logo

Google ADK

Use Pandadoc MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Pandadoc MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Pandadoc MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Pandadoc MCP with LlamaIndex

CrewAI logo

CrewAI

Use Pandadoc MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Pandadoc MCP with Pydantic AI

AutoGen logo

AutoGen

Use Pandadoc MCP with AutoGen

FAQ

Frequently asked questions

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

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 Pandadoc tools.

Yes, absolutely. You can configure which Pandadoc 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 Pandadoc data and credentials are handled as safely as possible.

Start with Pandadoc.It takes 30 seconds.

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

Start building