How to integrate Taggun MCP with CrewAI

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Taggun logo
CrewAI logo
divider

Introduction

This guide walks you through connecting Taggun to CrewAI using the Composio tool router. By the end, you'll have a working Taggun agent that can extract vendor and total from this receipt image url, list all line items from uploaded invoice link, validate this receipt url before submitting expense through natural language commands.

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

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

Also integrate Taggun with

TL;DR

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

The Taggun MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Taggun account. It provides structured and secure access to real-time receipt OCR and merchant management, so your agent can scan receipts, extract detailed data, validate image URLs, and manage merchant records on your behalf.

  • Instant receipt data extraction: Have your agent process receipt or invoice images via public URLs to pull out structured purchase data quickly and accurately.
  • Detailed line item analysis: Use verbose extraction to get comprehensive data including line items, merchant info, and confidence metrics from receipt images or PDFs.
  • Automated merchant registry management: Export the full list of known merchants for audits or synchronize merchant data directly through your agent.
  • Receipt image URL validation: Let your agent check if a receipt image URL meets campaign and validation requirements before processing.
  • Generate merchant mock CSVs for testing: Easily create sample merchant CSV files to test or bulk import merchant data as part of your automation workflow.

Supported Tools & Triggers

Tools
Add Merchant NameTool to add a merchant name keyword to your account's model for predicting merchant names.
Export Known MerchantsExport the complete list of known merchants used for merchant name normalization in Taggun.
Export Known Product CodesExport the complete list of known product codes used for product normalization and matching in Taggun.
Export Product CategoriesExport a list of product categories and descriptions used for product categorization in CSV format.
Generate Merchants CSVGenerate a CSV file with mock merchant data for testing purposes.
Import Known MerchantsImport a list of merchant names and addresses to normalize and match in CSV or TSV format.
Import Known Product CodesTool to import a list of product codes in CSV or TSV format for normalization and matching.
Import Product CategoriesImport a list of product categories and descriptions for product categorization.
Transcribe Receipt from Base64 Encoded ImageExtract structured data from a receipt or invoice using base64 encoded image data.
Transcribe Receipt Encoded VerboseTool to transcribe a receipt using base64 encoded image in JSON payload and return detailed results.
Transcribe Receipt File (Simple)Tool to upload a receipt or invoice image file and extract basic data including merchant name, total amount, tax amount, and date.
Process Receipt via URLExtract structured data from a receipt or invoice image using OCR.
URL ValidationTool to extract and validate receipt data from a URL.
URL VerboseTool to process a receipt or invoice from a URL for detailed data extraction.

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

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Taggun 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[mcp] python-dotenv
What's happening:
  • composio connects your agent to Taggun via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] 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
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

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

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")
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 Taggun MCP URL

Create a Composio Tool Router session for Taggun

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["taggun"])

url = session.mcp.url
What's happening:
  • You create a Taggun only session through Composio
  • Composio returns an MCP HTTP URL that exposes Taggun tools

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[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:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

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

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_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.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["taggun"],
)
url = session.mcp.url

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

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

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

Conclusion

You now have a CrewAI agent connected to Taggun through Composio's Tool Router. The agent can perform Taggun 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 Taggun MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Taggun MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Taggun MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Taggun MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Taggun MCP with Claude Cowork

Codex logo

Codex

Use Taggun MCP with Codex

OpenClaw logo

OpenClaw

Use Taggun MCP with OpenClaw

Hermes logo

Hermes

Use Taggun MCP with Hermes

CLI logo

CLI

Use Taggun MCP with CLI

Google ADK logo

Google ADK

Use Taggun MCP with Google ADK

LangChain logo

LangChain

Use Taggun MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Taggun MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Taggun MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Taggun MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Taggun 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 Taggun 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.

Get started for freeGet a demo↗