How to integrate Pdfmonkey MCP with CrewAI

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

Introduction

This guide walks you through connecting Pdfmonkey to CrewAI using the Composio tool router. By the end, you'll have a working Pdfmonkey agent that can generate pdf invoices from my template, download latest generated contract pdf file, create a new proposal template for sales, delete old pdf documents by document id through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Pdfmonkey account through Composio's Pdfmonkey 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 Pdfmonkey connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Pdfmonkey
  • Build a conversational loop where your agent can execute Pdfmonkey 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 Pdfmonkey MCP server, and what's possible with it?

The Pdfmonkey MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, or others directly to your Pdfmonkey account. It provides structured and secure access to your PDF automation workflows, so your agent can generate documents from templates, download PDFs, manage templates, and retrieve document details on your behalf.

  • Automated PDF generation: Instantly create new PDF documents from pre-built templates or custom data payloads, either asynchronously or waiting for immediate results.
  • Template management and updates: Let your agent create, fetch, or delete document templates to keep your PDF generation process organized and up to date.
  • Document retrieval and monitoring: Fetch the full details of any generated document, including metadata, logs, and download links for seamless workflow integration.
  • Secure PDF file download: Easily obtain presigned URLs to access or share generated PDF files, with automatic handling of expiring links.
  • Account and usage insights: Retrieve authenticated user information, such as quota, plan, and locale, to help monitor and manage your Pdfmonkey usage directly from your agent.

Supported Tools & Triggers

Tools
Create DocumentTool to create a Document.
Create Document SyncTool to create a document and wait for generation to finish.
Create TemplateTool to create a new Document Template.
Delete DocumentTool to delete a Document by its ID.
Delete PDFMonkey Document TemplateTool to delete a document template by ID.
Download Document FileTool to download a generated PDF file via a presigned URL.
Get Current UserTool to retrieve details about the currently authenticated user.
Get DocumentTool to fetch a Document by its ID.
Get DocumentCardTool to fetch a DocumentCard by ID.
Get Template by IDTool to fetch a Document Template by ID.
List DocumentCardsTool to list DocumentCards.
List PDF EnginesTool to list available PDF engines with deprecation metadata.
List Template CardsTool to list template cards for a workspace.
List WorkspacesTool to list workspaces (applications).
Preview DocumentTool to open a document preview via a PDF.
Preview TemplateTool to preview a template draft as a real PDF via the preview_url.
Update DocumentTool to update a Document’s payload, meta, or status.
Update Document TemplateTool to update a document template’s properties.
View Public Share LinkTool to download a publicly shared PDF via its permanent share link.

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 Pdfmonkey 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 Pdfmonkey 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 Pdfmonkey MCP URL

Create a Composio Tool Router session for Pdfmonkey

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["pdfmonkey"],
)
url = session.mcp.url
What's happening:
  • You create a Pdfmonkey only session through Composio
  • Composio returns an MCP HTTP URL that exposes Pdfmonkey 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="Pdfmonkey Assistant",
    goal="Help users interact with Pdfmonkey through natural language commands",
    backstory=(
        "You are an expert assistant with access to Pdfmonkey tools. "
        "You can perform various Pdfmonkey 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 Pdfmonkey 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 Pdfmonkey 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 Pdfmonkey 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_pdfmonkey_agent.py

Complete Code

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

python
# file: crewai_pdfmonkey_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 Pdfmonkey session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["pdfmonkey"],
    )
    url = session.mcp.url

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

    # Create Pdfmonkey assistant agent
    toolkit_agent = Agent(
        role="Pdfmonkey Assistant",
        goal="Help users interact with Pdfmonkey through natural language commands",
        backstory=(
            "You are an expert assistant with access to Pdfmonkey tools. "
            "You can perform various Pdfmonkey 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 Pdfmonkey 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 Pdfmonkey 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 Pdfmonkey through Composio's Tool Router. The agent can perform Pdfmonkey 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 Pdfmonkey MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Pdfmonkey MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Pdfmonkey MCP with Claude Agent SDK

Google ADK

Google ADK

Use Pdfmonkey MCP with Google ADK

LangChain

LangChain

Use Pdfmonkey MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Pdfmonkey MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Pdfmonkey MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Pdfmonkey MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Pdfmonkey 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 Pdfmonkey 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