How to integrate Api2pdf MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Api2pdf Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Api2pdf to CrewAI using the Composio tool router. By the end, you'll have a working Api2pdf agent that can merge monthly invoices into one pdf, extract specific pages from a large pdf, add custom header and footer to document, convert pdf report to html for web use through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Api2pdf account through Composio's Api2pdf 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 Api2pdf connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Api2pdf
  • Build a conversational loop where your agent can execute Api2pdf 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 Api2pdf MCP server, and what's possible with it?

The Api2pdf MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Api2pdf account. It provides structured and secure access to powerful PDF generation and manipulation features, so your agent can generate PDFs from HTML or URLs, merge or optimize documents, extract or reorder pages, and more—automatically and on your behalf.

  • PDF generation from web content: Instruct your agent to convert HTML or URLs into high-quality PDFs using engines like wkhtmltopdf or Headless Chrome.
  • Merge and optimize PDFs: Have your agent combine multiple PDFs into a single file or optimize existing documents to reduce file size without sacrificing quality.
  • Advanced PDF manipulation: Direct your agent to extract specific pages, reorder existing pages, or add custom headers and footers for consistent branding or page numbering.
  • Barcode and QR code generation: Let your agent instantly create barcode or QR code images from any text value, ready to embed in documents or use elsewhere.
  • Document conversion and preview: Ask your agent to convert PDFs to HTML with LibreOffice or generate thumbnail previews for quick visual reference.

Supported Tools & Triggers

Tools
Add Header FooterTool to add headers and footers to a pdf document.
Delete PDFTool to delete a previously generated pdf.
Extract PDF PagesTool to extract specific pages from a pdf document.
LibreOffice PDF to HTMLTool to convert a pdf document to html using libreoffice.
LibreOffice ThumbnailTool to generate a thumbnail image of a document using libreoffice.
Merge PDFsTool to merge multiple pdf documents into a single pdf.
Optimize PDFTool to optimize a pdf document to reduce file size while maintaining quality.
Reorder PDF PagesTool to reorder pages of a pdf document.
Generate Barcode or QR CodeTool to generate barcodes or qr codes using zebra crossing (zxing).

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 Api2pdf 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 Api2pdf 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 Api2pdf MCP URL

Create a Composio Tool Router session for Api2pdf

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["api2pdf"],
)
url = session.mcp.url
What's happening:
  • You create a Api2pdf only session through Composio
  • Composio returns an MCP HTTP URL that exposes Api2pdf 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="Api2pdf Assistant",
    goal="Help users interact with Api2pdf through natural language commands",
    backstory=(
        "You are an expert assistant with access to Api2pdf tools. "
        "You can perform various Api2pdf 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 Api2pdf 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 Api2pdf 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 Api2pdf 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_api2pdf_agent.py

Complete Code

Here's the complete code to get you started with Api2pdf and CrewAI:

python
# file: crewai_api2pdf_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 Api2pdf session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["api2pdf"],
    )
    url = session.mcp.url

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

    # Create Api2pdf assistant agent
    toolkit_agent = Agent(
        role="Api2pdf Assistant",
        goal="Help users interact with Api2pdf through natural language commands",
        backstory=(
            "You are an expert assistant with access to Api2pdf tools. "
            "You can perform various Api2pdf 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 Api2pdf 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 Api2pdf 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 Api2pdf through Composio's Tool Router. The agent can perform Api2pdf 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 Api2pdf MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Api2pdf MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Api2pdf MCP with Claude Agent SDK

Google ADK

Google ADK

Use Api2pdf MCP with Google ADK

LangChain

LangChain

Use Api2pdf MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Api2pdf MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Api2pdf MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Api2pdf MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Api2pdf MCP?

With a standalone Api2pdf MCP server, the agents and LLMs can only access a fixed set of Api2pdf tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Api2pdf 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 Api2pdf tools.

Can I manage the permissions and scopes for Api2pdf while using Tool Router?

Yes, absolutely. You can configure which Api2pdf 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 Api2pdf 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