How to Use the ComplyAdvantage MCP in AutoGen

Q: How do AutoGen agents collaborate on a ComplyAdvantage search?

One agent runs createsearch to get the raw matches, while a second agent evaluates the risk flags using getsearchdetails. They discuss the findings in a group chat to decide whether to approve the entity.

Q: Can AutoGen agents assign ComplyAdvantage searches to human users?

Yes, the agents can call listusers to see who is active, then use updatesearch to assign the flagged entity to a specific compliance officer.

Q: How do I acknowledge changes in monitored searches?

Call acknowledgemonitor when your agent detects a change in an entity's status. This clears the alert in your dashboard and signals that the change has been reviewed.

Run multi-agent debates over ComplyAdvantage risk profiles using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ComplyAdvantage MCP to AutoGen

Create your Vinkius account to connect ComplyAdvantage 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 ComplyAdvantage with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on compliance risk

`create_search` initiates the screening process within an AutoGen conversation using this MCP Server. The customer agent pushes for speed, while the compliance agent evaluates the risk. This setup prevents automatic rejections by forcing a structured debate over borderline matches. The agents negotiate until they reach a consensus based on your risk tolerance.

Collaborative audit trail creation

`create_comment` logs the final consensus reached by your AutoGen agents directly onto the ComplyAdvantage search record via the MCP Server. When the agents agree on a risk level, they document their reasoning automatically. You can also use `delete_search_tag` to clean up temporary flags once the agents resolve a dispute. This keeps your compliance dashboard clean without manual intervention.

Automated escalation via MCP Server tools

`update_search_monitors` allows your AutoGen agents to activate continuous tracking when they agree an entity requires ongoing surveillance. If the debate agent flags a medium-risk profile, it initiates monitoring. The system uses `list_users` to find available compliance officers and assign them to the case using `update_search`. This bridges the gap between automated multi-agent reasoning and human oversight.

Setup guide

Set up ComplyAdvantage 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 ComplyAdvantage 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="ComplyAdvantage_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ComplyAdvantage 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="ComplyAdvantage_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ComplyAdvantage 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 ComplyAdvantage. 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 ComplyAdvantage 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 ComplyAdvantage MCP in AutoGen

One agent runs `create_search` to get the raw matches, while a second agent evaluates the risk flags using `get_search_details`. They discuss the findings in a group chat to decide whether to approve the entity.

Yes, the agents can call `list_users` to see who is active, then use `update_search` to assign the flagged entity to a specific compliance officer.

You should set strict execution limits on your agents' tool calling loops. This prevents them from calling `get_search` repeatedly when debating complex risk profiles.

Call `acknowledge_monitor` when your agent detects a change in an entity's status. This clears the alert in your dashboard and signals that the change has been reviewed.

Yes, the MCP Server runs in a secure, isolated V8 sandbox that processes your AML screening data in memory. No search history or PEP details are stored or logged by Vinkius.

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