How to integrate Pandadoc MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Pandadoc Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Pandadoc to CrewAI using the Composio tool router. By the end, you'll have a working Pandadoc agent that can create a new contract from pdf upload, add an attachment to a draft proposal, list details of my latest templates, create a contact with company information through natural language commands.

This guide will help you understand how to give your CrewAI 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.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Pandadoc connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Pandadoc
  • Build a conversational loop where your agent can execute Pandadoc operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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.

Supported Tools & Triggers

Tools
Create ContactThis tool creates a new contact in pandadoc.
Create Document AttachmentCreates and adds an attachment to a pandadoc document.
Create Document from File UploadCreates a new document in pandadoc by uploading a file (pdf, docx, etc.
Create Document FolderCreates a new folder in pandadoc to organize documents.
Create or Update ContactThis tool creates a new contact or updates an existing one in pandadoc based on the email address.
Create TemplateThis tool allows users to create a new template in pandadoc from a pdf file or from scratch.
Create PandaDoc WebhookCreates a new webhook subscription in pandadoc to receive notifications about specific events.
Delete ContactThis tool allows you to delete a contact from your pandadoc account.
Delete TemplateThis tool deletes a specific template from pandadoc.
Get Template DetailsThis tool retrieves detailed information about a specific template by its id.
List ContactsA tool to list and search contacts in pandadoc.
List Document FoldersThis tool retrieves a list of all document folders in pandadoc.
List TemplatesThis tool retrieves a list of all templates available in the pandadoc account.
Move Document to FolderThis tool allows users to move a document to a specific folder within their pandadoc account.

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 starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Pandadoc connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Pandadoc via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_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 with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Pandadoc MCP URL

Create a Composio Tool Router session for Pandadoc

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["pandadoc"],
)
url = session.mcp.url
What's happening:
  • You create a Pandadoc only session through Composio
  • Composio returns an MCP HTTP URL that exposes Pandadoc tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Pandadoc Assistant",
    goal="Help users interact with Pandadoc through natural language commands",
    backstory=(
        "You are an expert assistant with access to Pandadoc tools. "
        "You can perform various Pandadoc operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Pandadoc MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Pandadoc operations.\n")

conversation_context = ""

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

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

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Pandadoc related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_pandadoc_agent.py

Complete Code

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

python
# file: crewai_pandadoc_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Pandadoc session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["pandadoc"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Pandadoc assistant agent
    toolkit_agent = Agent(
        role="Pandadoc Assistant",
        goal="Help users interact with Pandadoc through natural language commands",
        backstory=(
            "You are an expert assistant with access to Pandadoc tools. "
            "You can perform various Pandadoc operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Pandadoc operations.\n")

    conversation_context = ""

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

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

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Pandadoc related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Pandadoc through Composio's Tool Router. The agent can perform Pandadoc operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Pandadoc MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Pandadoc MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Pandadoc MCP with Claude Agent SDK

Google ADK

Google ADK

Use Pandadoc MCP with Google ADK

LangChain

LangChain

Use Pandadoc MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Pandadoc MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Pandadoc MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Pandadoc MCP with LlamaIndex

FAQ

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

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.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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.

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

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.

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 Pandadoc data and credentials are handled as safely as possible.

Used by agents from

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