# How to integrate Fraudlabs pro MCP with Autogen ```json { "title": "How to integrate Fraudlabs pro MCP with Autogen", "toolkit": "Fraudlabs pro", "toolkit_slug": "fraudlabs_pro", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/fraudlabs_pro/framework/autogen", "markdown_url": "https://composio.dev/toolkits/fraudlabs_pro/framework/autogen.md", "updated_at": "2026-05-12T10:12:16.845Z" } ``` ## Introduction This guide walks you through connecting Fraudlabs pro to AutoGen using the Composio tool router. By the end, you'll have a working Fraudlabs pro agent that can screen this new order for fraud risk, send sms otp to verify customer phone, get analysis result for order 123456 through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Fraudlabs pro account through Composio's Fraudlabs pro MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Fraudlabs pro with - [OpenAI Agents SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/fraudlabs_pro/framework/codex) - [OpenClaw](https://composio.dev/toolkits/fraudlabs_pro/framework/openclaw) - [Hermes](https://composio.dev/toolkits/fraudlabs_pro/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/fraudlabs_pro/framework/cli) - [Google ADK](https://composio.dev/toolkits/fraudlabs_pro/framework/google-adk) - [LangChain](https://composio.dev/toolkits/fraudlabs_pro/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/fraudlabs_pro/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/fraudlabs_pro/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/fraudlabs_pro/framework/crew-ai) ## TL;DR Here's what you'll learn: - Get and set up your OpenAI and Composio API keys - Install the required dependencies for Autogen and Composio - Initialize Composio and create a Tool Router session for Fraudlabs pro - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Fraudlabs pro tools - Run a live chat loop where you ask the agent to perform Fraudlabs pro operations ## What is AutoGen? Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows. Key features include: - Multi-Agent Systems: Build collaborative agent workflows - MCP Workbench: Native support for Model Context Protocol tools - Streaming HTTP: Connect to external services through streamable HTTP - AssistantAgent: Pre-built agent class for tool-using assistants ## What is the Fraudlabs pro MCP server, and what's possible with it? The Fraudlabs pro MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fraudlabs Pro account. It provides structured and secure access to your fraud detection and order screening tools, so your agent can perform actions like screening transactions, sending SMS OTPs, retrieving fraud analysis results, and managing reseller subscriptions on your behalf. - Real-time fraud screening for orders: Instantly have your agent assess the risk of new transactions before fulfillment to minimize chargebacks and detect suspicious activity. - Automated SMS OTP verification: Directly send one-time passwords to customers via SMS and verify phone numbers for added transaction security. - Retrieve and analyze fraud results: Quickly pull fraud analysis reports on previously screened orders for smarter decision-making and audit trails. - Feedback and continuous learning: Submit order feedback—approved or rejected—to improve future fraud detection accuracy and adapt to evolving threats. - Reseller account management: Automate account creation and manage subscription plans for resellers directly from your agent, streamlining onboarding and upgrades. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `FRAUDLABS_PRO_CREATE_ACCOUNT` | Create FraudLabs Pro Reseller Sub-Account | Creates a new FraudLabs Pro user account under a reseller account. Requires a Reseller API key (not a regular API key). Use this action to provision new sub-accounts for customers when operating as a FraudLabs Pro reseller. Returns account credentials (username and password) upon successful creation. Prerequisites: - Must have a FraudLabs Pro Reseller account (apply at https://www.fraudlabspro.com/reseller/program) - Requires valid Reseller API key (different from standard FraudLabs Pro API key) - All required fields must contain valid data matching FraudLabs Pro validation rules Important: - Phone numbers should contain only digits (no +, -, spaces, or parentheses) - Country must be valid ISO 3166-1 alpha-2 code (e.g., US, GB, CA) - Industry must be a valid ID from 1-14 | | `FRAUDLABS_PRO_FLP_FEEDBACK_ORDER` | FLP Feedback Order | Submit fraud screening feedback to improve FraudLabs Pro's machine learning model. Use this after reviewing a screened order to mark it as approved, rejected, or blacklisted. This feedback trains the algorithm to better detect fraud patterns in future transactions. | | `FRAUDLABS_PRO_FLP_SCREEN_ORDER` | FraudLabs Pro Screen Order | Tool to screen orders for fraud. Use when you need to assess transaction risk before fulfillment. | | `FRAUDLABS_PRO_GET_ORDER_RESULT2` | Get FraudLabs Pro Order Result (v2) | Tool to retrieve an existing transaction from FraudLabs Pro fraud detection system using the v2 API. This API is only available for paid plans. | | `FRAUDLABS_PRO_GET_SMS_VERIFICATION_RESULT` | Get SMS Verification Result | Verify an OTP (one-time password) received via SMS. Returns 'Y' if the OTP is valid, 'N' if invalid or expired. Must be called after using Send SMS Verification to obtain a transaction ID. | | `FRAUDLABS_PRO_SEND_SMS_VERIFICATION` | Send SMS OTP Verification | Sends an SMS message containing a one-time password (OTP) to verify a user's phone number. The API generates a random 6-digit OTP, replaces the placeholder in your message template, and sends the SMS to the recipient. Returns a transaction ID that you must use with the Get SMS Verification Result action to verify the OTP the user enters. Testing: Use phone number '+11' for sandbox testing (no credits deducted). For verification testing with sandbox number, use OTP '123456'. | | `FRAUDLABS_PRO_SUBSCRIBE_PLAN` | Subscribe Reseller Plan | Tool to subscribe a reseller account to a specific plan. Use after obtaining a reseller API key and selecting a plan. Example: Subscribe user "john_doe" to the MICRO plan. | | `FRAUDLABS_PRO_WEBHOOK_ORDER_STATUS_CHANGED` | Test Order Status Changed Webhook Delivery | Tool to send a test webhook payload to the provided callback URL for FraudLabs Pro order status change notifications. This helps validate your endpoint behavior. Important: FraudLabs Pro webhook registration must be configured manually via dashboard. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Fraudlabs pro MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Fraudlabs pro. Instead of manually wiring Fraudlabs pro APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites You will need: - A Composio API key - An OpenAI API key (used by Autogen's OpenAIChatCompletionClient) - A Fraudlabs pro account you can connect to Composio - Some basic familiarity with Autogen and Python async ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies Install Composio, Autogen extensions, and dotenv. What's happening: - composio connects your agent to Fraudlabs pro via MCP - autogen-agentchat provides the AssistantAgent class - autogen-ext-openai provides the OpenAI model client - autogen-ext-tools provides MCP workbench support ```bash pip install composio python-dotenv pip install autogen-agentchat autogen-ext-openai autogen-ext-tools ``` ### 3. Set up environment variables Create a .env file in your project folder. What's happening: - COMPOSIO_API_KEY is required to talk to Composio - OPENAI_API_KEY is used by Autogen's OpenAI client - USER_ID is how Composio identifies which user's Fraudlabs pro connections to use ```bash COMPOSIO_API_KEY=your-composio-api-key OPENAI_API_KEY=your-openai-api-key USER_ID=your-user-identifier@example.com ``` ### 4. Import dependencies and create Tool Router session What's happening: - load_dotenv() reads your .env file - Composio(api_key=...) initializes the SDK - create(...) creates a Tool Router session that exposes Fraudlabs pro tools - session.mcp.url is the MCP endpoint that Autogen will connect to ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Fraudlabs pro session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["fraudlabs_pro"] ) url = session.mcp.url ``` ### 5. Configure MCP parameters for Autogen Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for. What's happening: - url points to the Tool Router MCP endpoint from Composio - timeout is the HTTP timeout for requests - sse_read_timeout controls how long to wait when streaming responses - terminate_on_close=True cleans up the MCP server process when the workbench is closed ```python # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) ``` ### 6. Create the model client and agent What's happening: - OpenAIChatCompletionClient wraps the OpenAI model for Autogen - McpWorkbench connects the agent to the MCP tools - AssistantAgent is configured with the Fraudlabs pro tools from the workbench ```python # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Fraudlabs pro assistant agent with MCP tools agent = AssistantAgent( name="fraudlabs_pro_assistant", description="An AI assistant that helps with Fraudlabs pro operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) ``` ### 7. Run the interactive chat loop What's happening: - The script prompts you in a loop with You: - Autogen passes your input to the model, which decides which Fraudlabs pro tools to call via MCP - agent.run_stream(...) yields streaming messages as the agent thinks and calls tools - Typing exit, quit, or bye ends the loop ```python print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Fraudlabs pro related question or task to the agent.\n") # Conversation loop while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, "content") and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") ``` ## Complete Code ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Fraudlabs pro session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["fraudlabs_pro"] ) url = session.mcp.url # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Fraudlabs pro assistant agent with MCP tools agent = AssistantAgent( name="fraudlabs_pro_assistant", description="An AI assistant that helps with Fraudlabs pro operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Fraudlabs pro related question or task to the agent.\n") # Conversation loop while True: user_input = input("You: ").strip() if user_input.lower() in ['exit', 'quit', 'bye']: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, 'content') and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") if __name__ == "__main__": asyncio.run(main()) ``` ## Conclusion You now have an Autogen assistant wired into Fraudlabs pro through Composio's Tool Router and MCP. From here you can: - Add more toolkits to the toolkits list, for example notion or hubspot - Refine the agent description to point it at specific workflows - Wrap this script behind a UI, Slack bot, or internal tool Once the pattern is clear for Fraudlabs pro, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Fraudlabs pro MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/fraudlabs_pro/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/fraudlabs_pro/framework/codex) - [OpenClaw](https://composio.dev/toolkits/fraudlabs_pro/framework/openclaw) - [Hermes](https://composio.dev/toolkits/fraudlabs_pro/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/fraudlabs_pro/framework/cli) - [Google ADK](https://composio.dev/toolkits/fraudlabs_pro/framework/google-adk) - [LangChain](https://composio.dev/toolkits/fraudlabs_pro/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/fraudlabs_pro/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/fraudlabs_pro/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/fraudlabs_pro/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/fraudlabs_pro/framework/crew-ai) ## Related Toolkits - [Addresszen](https://composio.dev/toolkits/addresszen) - Addresszen is a real-time address autocomplete and verification service. It helps capture accurate, deliverable addresses with instant suggestions and validation. - [Asin data api](https://composio.dev/toolkits/asin_data_api) - Asin data api gives you detailed, real-time product data from Amazon, including price, rank, and reviews. Perfect for e-commerce pros and data-driven marketers who need instant marketplace insights. - [Baselinker](https://composio.dev/toolkits/baselinker) - BaseLinker is an all-in-one e-commerce management platform connecting stores, marketplaces, carriers, and more. It streamlines order processing, inventory control, and automates your sales operations. - [Bestbuy](https://composio.dev/toolkits/bestbuy) - Best Buy is a leading retailer offering APIs for product, store, and recommendation data. Instantly access up-to-date retail insights for smarter shopping and decision-making. - [Btcpay server](https://composio.dev/toolkits/btcpay_server) - BTCPay Server is a free, open-source, self-hosted Bitcoin payment processor. It lets merchants accept Bitcoin payments directly, cutting out middlemen and boosting privacy. - [Cdr platform](https://composio.dev/toolkits/cdr_platform) - Cdr platform is an API for purchasing carbon dioxide removal services. It enables businesses to offset emissions by accessing verified carbon removal projects. - [Cloudcart](https://composio.dev/toolkits/cloudcart) - CloudCart is an e-commerce platform for building and managing online stores. It helps businesses streamline product listings, orders, and customer engagement. - [Countdown api](https://composio.dev/toolkits/countdown_api) - Countdown API gives you real-time, structured eBay product data, reviews, and seller feedback. Perfect for powering price monitoring, product research, or marketplace analytics workflows. - [Dpd2](https://composio.dev/toolkits/dpd2) - Dpd2 is a robust email management platform for handling, sorting, and automating email workflows. Streamline your communications and boost productivity with advanced sorting, labeling, and response tools. - [Finerworks](https://composio.dev/toolkits/finerworks) - FinerWorks is an online platform for fine art and photo printing services. Artists and photographers use it to order custom prints and manage print inventory efficiently. - [Fingertip](https://composio.dev/toolkits/fingertip) - Fingertip is a business management platform for selling, booking, and customer engagement—all from a single link. It helps businesses streamline operations and connect with customers across social channels. - [Gift up](https://composio.dev/toolkits/gift_up) - Gift Up! is a digital platform for selling, managing, and redeeming gift cards online. It streamlines promotions and gift card transactions for businesses and their customers. - [Goody](https://composio.dev/toolkits/goody) - Goody is a gifting platform that lets users send gifts and physical products without handling logistics. It streamlines gifting by managing delivery, fulfillment, and recipient experience. - [Gumroad](https://composio.dev/toolkits/gumroad) - Gumroad is a platform for selling digital products, physical goods, and memberships with a simple checkout and marketing tools. It streamlines creator payouts and helps you grow your audience effortlessly. - [Instacart](https://composio.dev/toolkits/instacart) - Instacart is an online grocery delivery and pickup service platform. It lets you discover local retailers and create shoppable lists and recipes with ease. - [Junglescout](https://composio.dev/toolkits/junglescout) - Junglescout is an Amazon product research and analytics platform for sellers. It delivers sales estimates, competitive insights, and optimization tools to boost your Amazon business. - [Ko fi](https://composio.dev/toolkits/ko_fi) - Ko-fi is a platform that lets creators receive donations, memberships, and sales from fans. It helps creators monetize their work and grow their audience with minimal friction. - [Lemon squeezy](https://composio.dev/toolkits/lemon_squeezy) - Lemon Squeezy is a payments and subscription platform built for software companies. It makes managing payments, taxes, and customer subscriptions effortless. - [Loyverse](https://composio.dev/toolkits/loyverse) - Loyverse is a point-of-sale (POS) platform for small businesses, offering tools for sales, inventory, and customer loyalty. It helps streamline retail operations and boost customer engagement. - [Memberstack](https://composio.dev/toolkits/memberstack) - Memberstack lets you add user authentication, payments, and member management to your website—no backend code required. Easily manage your site's members and subscriptions from a single platform. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Fraudlabs pro MCP? With a standalone Fraudlabs pro MCP server, the agents and LLMs can only access a fixed set of Fraudlabs pro tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Fraudlabs pro and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Autogen? Yes, you can. Autogen 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 Fraudlabs pro tools. ### Can I manage the permissions and scopes for Fraudlabs pro while using Tool Router? Yes, absolutely. You can configure which Fraudlabs pro 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 Fraudlabs pro data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)