# How to integrate Virustotal MCP with Autogen

```json
{
  "title": "How to integrate Virustotal MCP with Autogen",
  "toolkit": "Virustotal",
  "toolkit_slug": "virustotal",
  "framework": "AutoGen",
  "framework_slug": "autogen",
  "url": "https://composio.dev/toolkits/virustotal/framework/autogen",
  "markdown_url": "https://composio.dev/toolkits/virustotal/framework/autogen.md",
  "updated_at": "2026-05-12T10:29:51.341Z"
}
```

## Introduction

This guide walks you through connecting Virustotal to AutoGen using the Composio tool router. By the end, you'll have a working Virustotal agent that can scan this file hash for malware, get analysis report for suspicious url, retrieve domain reputation details through natural language commands.
This guide will help you understand how to give your AutoGen agent real control over a Virustotal account through Composio's Virustotal MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Virustotal with

- [ChatGPT](https://composio.dev/toolkits/virustotal/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/virustotal/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/virustotal/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/virustotal/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/virustotal/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/virustotal/framework/codex)
- [Cursor](https://composio.dev/toolkits/virustotal/framework/cursor)
- [VS Code](https://composio.dev/toolkits/virustotal/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/virustotal/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/virustotal/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/virustotal/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/virustotal/framework/cli)
- [Google ADK](https://composio.dev/toolkits/virustotal/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/virustotal/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/virustotal/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/virustotal/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/virustotal/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/virustotal/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 Virustotal
- Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
- Configure an Autogen AssistantAgent that can call Virustotal tools
- Run a live chat loop where you ask the agent to perform Virustotal 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 Virustotal MCP server, and what's possible with it?

The Virustotal MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Virustotal account. It provides structured and secure access to malicious file, URL, domain, and IP analysis, so your agent can perform actions like scanning files, retrieving threat reports, investigating domains, and posting comments or verdicts on your behalf.
- Comprehensive threat analysis retrieval: Instantly fetch detailed reports on files, URLs, domains, or IP addresses to understand their security reputation and scan results from dozens of antivirus engines.
- Relationship and metadata insights: Have your agent explore related entities—such as domains linked to a file, or files associated with an IP address—along with receiving broad metadata about available VirusTotal operations.
- Automated commenting and feedback: Use your agent to post contextual comments on any analyzed resource, making collaboration and documentation of findings much easier.
- Community-driven voting: Submit harmless or malicious verdicts on files and URLs after reviewing analysis, helping to crowdsource threat intelligence and improve detection accuracy.
- Latest user comment retrieval: Let your agent pull up the most recent comments on a file, URL, domain, or IP address to quickly access community feedback and insights.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `VIRUSTOTAL_ADD_COMMENT` | Add VirusTotal Comment | Tool to add a comment to a VirusTotal resource (file, URL, domain, or IP address). Use after analyzing a resource to leave contextual feedback. Provide exactly one identifier per call. |
| `VIRUSTOTAL_ADD_VOTE` | Add Vote | Tool to add a vote (harmless/malicious) to a VirusTotal resource. Use after reviewing analysis results to submit your verdict. |
| `VIRUSTOTAL_GET_ANALYSIS` | Get Analysis Report | Tool to retrieve the analysis report of a file or URL submission. Use after obtaining an analysis ID to fetch its detailed report. Analysis results may be incomplete immediately after submission; poll until the report status is 'completed' before treating results as final. |
| `VIRUSTOTAL_GET_COMMENTS` | Get comments | Tool to retrieve the latest comments on a VirusTotal resource. Use when you need to review user-generated comments for a file, URL, domain, or IP after obtaining its identifier. |
| `VIRUSTOTAL_GET_DOMAIN_RELATIONSHIPS` | Get Domain Relationships | Tool to retrieve relationship objects for a given domain. Use when you have a domain and need to explore its related entities. |
| `VIRUSTOTAL_GET_DOMAIN_REPORT` | Get Domain Report | Tool to retrieve the analysis report of a domain. Use when you need detailed insight on a domain's reputation and analysis stats. No malicious signals on obscure or low-traffic domains may indicate limited analysis history rather than safety — treat sparse results as 'unknown', not 'safe'. Covers external OSINT only (reputation, malware, SSL posture); cannot analyze internal/private assets. |
| `VIRUSTOTAL_GET_FILE_REPORT` | Get File Report | Tool to retrieve the analysis report of a file. Use when you have a file's hash and need detailed scan metadata. Recently submitted files may return partial results; retry after a short delay before treating the report as final. |
| `VIRUSTOTAL_GET_IP_ADDRESS_RELATIONSHIPS` | Get IP Address Relationships | Tool to retrieve objects related to a specific IP address by relationship type. Use when you have an IP and need to explore connected files, URLs, or other entities. |
| `VIRUSTOTAL_GET_IP_ADDRESS_REPORT` | Get IP Address Report | Tool to retrieve the analysis report of an IP address. Use when you need detailed insight on an IP's reputation, ASN, country, and analysis stats. Low or zero detections indicate unknown risk, not safety — treat sparse data accordingly. Provides external OSINT only; insufficient as standalone compliance evidence. |
| `VIRUSTOTAL_GET_METADATA` | Get VirusTotal Metadata | Tool to retrieve VirusTotal metadata. Use when you need information about available privileges, relationships between resources (like files, domains, IPs, URLs), and supported antivirus engines. |
| `VIRUSTOTAL_GET_URL_REPORT` | Get URL Report | Tool to retrieve the analysis report of a URL. Use when you have a URL identifier (base64-url without padding) and need detailed scan results, reputation, and metadata. Results may be incomplete immediately after submission; retry with short delays if scan engines are still processing before treating the report as final. |
| `VIRUSTOTAL_GET_VOTES` | Get Votes | Tool to retrieve votes on files, URLs, domains, or IP addresses. Use when you need to view community votes for a given object. |
| `VIRUSTOTAL_RESCAN_FILE` | Rescan File | Tool to re-analyze a previously submitted file. Use when you need updated analysis results after an initial scan. |
| `VIRUSTOTAL_SCAN_URL` | Scan URL | Tool to submit a URL for scanning. Use when you have a URL and need to submit it to VirusTotal to obtain an analysis ID for later retrieval. The returned analysis ID is preliminary — scanning engines may not have finished. Poll VIRUSTOTAL_GET_URL_REPORT with the ID using short delays to retrieve complete results. |
| `VIRUSTOTAL_SEARCH` | Search VirusTotal | Tool to search for objects in the VirusTotal database. Use when locating files, URLs, domains, IPs, or comments matching a query. Supports pagination with limit and cursor. |
| `VIRUSTOTAL_UPLOAD_FILE` | Upload File | Tool to upload a file for scanning. Use when you have binary file content ready to submit for VirusTotal analysis. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Virustotal MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Virustotal. Instead of manually wiring Virustotal 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 Virustotal 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 Virustotal 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 Virustotal 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 Virustotal 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 Virustotal session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["virustotal"]
    )
    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 Virustotal 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 Virustotal assistant agent with MCP tools
    agent = AssistantAgent(
        name="virustotal_assistant",
        description="An AI assistant that helps with Virustotal 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 Virustotal 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 Virustotal 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 Virustotal session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["virustotal"]
    )
    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 Virustotal assistant agent with MCP tools
        agent = AssistantAgent(
            name="virustotal_assistant",
            description="An AI assistant that helps with Virustotal 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 Virustotal 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 Virustotal 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 Virustotal, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

## How to build Virustotal MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/virustotal/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/virustotal/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/virustotal/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/virustotal/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/virustotal/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/virustotal/framework/codex)
- [Cursor](https://composio.dev/toolkits/virustotal/framework/cursor)
- [VS Code](https://composio.dev/toolkits/virustotal/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/virustotal/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/virustotal/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/virustotal/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/virustotal/framework/cli)
- [Google ADK](https://composio.dev/toolkits/virustotal/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/virustotal/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/virustotal/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/virustotal/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/virustotal/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/virustotal/framework/crew-ai)

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Virustotal MCP?

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

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

Yes, absolutely. You can configure which Virustotal 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 Virustotal data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)