How to integrate Pdf co MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Pdf co Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Pdf co to LlamaIndex using the Composio tool router. By the end, you'll have a working Pdf co agent that can extract invoice data from uploaded pdf file, convert excel spreadsheet at url to json, generate a qr code for a payment link, merge multiple pdf files into a single document through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Pdf co account through Composio's Pdf co 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:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Pdf co
  • Connect LlamaIndex to the Pdf co MCP server
  • Build a Pdf co-powered agent using LlamaIndex
  • Interact with Pdf co through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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

The Pdf co MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pdf co account. It provides structured and secure access to your PDF.co capabilities, so your agent can extract data, generate documents, convert files, process barcodes, and manage asynchronous jobs on your behalf.

  • Automated PDF data extraction and parsing: Let your agent extract structured data from PDFs using templates or parse documents for key information—perfect for receipts, invoices, and more.
  • PDF creation, splitting, and merging: Generate new PDF files, combine multiple PDFs, or split documents into separate files without manual intervention.
  • File format conversion: Seamlessly convert Excel files to CSV, HTML, JSON, text, or XML, enabling efficient data analysis and workflow automation.
  • Barcode generation and processing: Instantly create various barcode formats (QR codes, Code128, PDF417, etc.) or encode data into barcodes for labeling and tracking.
  • Job management and file uploads: Upload documents to PDF.co, track the status of asynchronous jobs, and retrieve results—all through your agent, hands-free.

Supported Tools & Triggers

Tools
Get Account Balance InfoTool to get account balance info.
Generate BarcodeTool to generate barcode images (qr, code128, code39, pdf417, etc.
Convert Excel to CSVTool to convert an excel file (xls/xlsx) to csv.
Convert Excel to HTMLTool to convert an excel file to html.
Convert Excel to JSONTool to convert an online excel or csv file to json format.
Convert Excel to TextTool to convert excel files to plain text.
Convert Excel to XMLTool to convert an excel file to xml.
Document ParserTool to parse documents based on predefined templates to extract structured data.
Upload FileTool to upload a local file to pdf.
Check Job StatusTool to check status and result of an asynchronous job.
Add Content to PDFTool to add content to an existing pdf.
Change PDF Text SearchableTool to make pdf text searchable using ocr.
Delete PDF PagesTool to delete specific pages from a pdf file.
Extract PDF AttachmentsTool to extract embedded attachments from a pdf.
Find Text in PDFTool to find text in a pdf document.
PDF Forms Info ReaderTool to extract form field information from a pdf.
Convert Text to PDFTool to convert plain text data to pdf.
Convert Email to PDFTool to convert email files (.
Convert HTML to PDFTool to convert html code or webpage url into a pdf document.
PDF Info ReaderTool to retrieve detailed information and metadata of a pdf.
Merge PDFsTool to merge multiple pdf files into one document.
Rotate PDF PagesTool to rotate selected pages in a pdf.
Search and Delete Text in PDFTool to search for and delete text in a pdf by keyword or regex.
Search and Replace Text in PDFTool to search for and replace text in a pdf document.
Split PDFTool to split a pdf into multiple files by page ranges.
Convert PDF to CSVTool to convert pdf or scanned images to csv format.
Convert PDF to HTMLTool to convert pdf documents to html.
Convert PDF to ImageTool to convert pdf pages to images (png, jpg, tiff).
Convert PDF to JSONTool to convert pdf or scanned images to json format.
Convert PDF to TextTool to convert pdf or scanned images to plain text.
Convert PDF to XLSTool to convert pdf or scanned images to xls format.
Convert PDF to XLSXTool to convert pdf or scanned images to xlsx (excel) format.
Convert PDF to XMLTool to convert pdf or scanned images to xml format.

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 you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Pdf co account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Pdf co

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Pdf co access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called pdf co_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["pdf_co"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Pdf co actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Pdf co actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, pdf co)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Pdf co tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Pdf co database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Pdf co

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Pdf co, then start asking questions.

Complete Code

Here's the complete code to get you started with Pdf co and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["pdf_co"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Pdf co actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Pdf co actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Pdf co to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Pdf co tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Pdf co MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Pdf co MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Pdf co MCP with Claude Agent SDK

Google ADK

Google ADK

Use Pdf co MCP with Google ADK

LangChain

LangChain

Use Pdf co MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Pdf co MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Pdf co MCP with Mastra AI

CrewAI

CrewAI

Use Pdf co MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Pdf co MCP?

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Pdf co tools.

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

Yes, absolutely. You can configure which Pdf co 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 Pdf co 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.

Book a call↗Get started for free