How to Use the Have I Been Pwned MCP in AutoGen

Q: How do I install Have I Been Pwned for AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with your MCP Server parameters to fetch the tool definitions, then pass them to your AssistantAgent constructor.

Give your AutoGen agents access to global breach data. Let security and ops agents debate password rotation policies based on hard evidence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Have I Been Pwned MCP to AutoGen

Create your Vinkius account to connect Have I Been Pwned to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Have I Been Pwned with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel multi-agent security debates

The `search_account_breaches` tool feeds empirical evidence into your AutoGen conversations. A security agent pulls the breach history for a specific email address. It then passes that data to an operations agent to determine if a forced password reset is necessary. When agents disagree, they use `get_breach_details` to pull more context. If the breach only exposed usernames and not passwords, the ops agent might argue against a disruptive reset. The integration provides the raw facts they need to reach a consensus.

Verify hashes with the MCP Server

The `check_password_safety` tool lets your agents verify if a specific password hash exists in known leaks. Your security agent runs the check and alerts the group if the hash returns a positive hit. The conversation shifts from theoretical risk to immediate remediation. AutoGen handles the schema conversion automatically via the adapter. Your agents do not need custom code to understand the k-anonymity response. They just read the tool output and continue their negotiation.

Track raw text dumps collaboratively

The `search_account_pastes` tool allows your threat hunting agent to scan public text bins for exposed accounts. Pastes often indicate an active, unindexed attack. The agent flags these hits for the rest of the swarm to analyze. Meanwhile, another agent runs `list_all_breaches` to see if those pastes correlate with a newly announced corporate leak. You build a system where multiple AI personas work together to connect the dots. This beats a static script any day.

Setup guide

Set up Have I Been Pwned MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Have I Been Pwned tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Have I Been Pwned_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Have I Been Pwned data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Have I Been Pwned_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Have I Been Pwned data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Have I Been Pwned. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Have I Been Pwned now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Have I Been Pwned MCP in AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with your MCP Server parameters to fetch the tool definitions, then pass them to your `AssistantAgent` constructor.

Yes. Once you provide the tools to the agent, it decides when to call them based on the conversation context. You do not need to manually script the triggers.

If the API returns a rate limit or a 404, the adapter feeds that error straight back into the chat. The agent reads the error message and decides whether to retry or try a different approach.

The adapter supports both stdio and Streamable HTTP transports. You configure this when initializing the server parameters in your Python script.

The underlying MCP Server relies on a mathematical k-anonymity model. Your local script hashes the password and only sends a five-character prefix over the network. The provider returns all matching suffixes, keeping the actual credential completely hidden from network sniffers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript