How to Use the ComplyAdvantage MCP in LangChain

Q: Can I trace ComplyAdvantage tool execution using LangSmith?

Yes, every call to tools like getsearchdetails or updatesearchmonitors is fully traced. You will see exact latency, token usage, and payload data in your LangSmith dashboard.

Q: How do I filter out false positives during screening?

Use the fuzziness parameters in createsearch to adjust match sensitivity. Your agent can then run updatesearchentities to whitelist known safe entities based on your risk thresholds.

Run multi-step AML screening chains in LangChain using live ComplyAdvantage compliance checks.

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 LangChain

Create your Vinkius account to connect ComplyAdvantage to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chained AML screening pipelines with LangChain

`create_search` kicks off the verification sequence inside your LangChain runnable sequence using this MCP Server. Your agent takes the raw user registration data, structures it, and instantly initiates the sanctions check. Once the search completes, the agent pipes the output directly to `get_search_details` to extract risk flags. No manual parsing is required because the output format matches your chain's schema.

Automated remediation and monitoring loops

`update_search_monitors` controls the continuous risk tracking state for flagged entities directly from your agent's execution path via the MCP Server. If the initial search returns PEP or sanction hits, your LangChain agent automatically triggers this tool to keep watch. You can also run `create_comment` to document the exact path the agent took when resolving a flag. This creates a clean audit trail in your LangSmith trace.

Compliance state management via MCP Server

`update_search` modifies the assignee and status of a flagged entity when your LangGraph state machine hits a manual review node. When a high-risk hit is found, the graph transitions to an offline state and updates the compliance dashboard. The agent uses `list_searches` to check if the entity has been screened before proceeding with new transactions. This keeps your graph execution fast by avoiding redundant API calls.

Setup guide

Set up ComplyAdvantage MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ComplyAdvantage tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "complyadvantage-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ComplyAdvantage transactions"
    })
    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 LangChain

You should configure standard LangChain retry behavior on your runnables. When `create_search` hits a rate limit, the adapter backs off and retries automatically before continuing the chain.

Yes, every call to tools like `get_search_details` or `update_search_monitors` is fully traced. You will see exact latency, token usage, and payload data in your LangSmith dashboard.

You can use LangChain's persistent memory or session states to store the search IDs returned by `create_search`. This allows your agent to reference previous results using `get_search` later in the conversation.

Use the fuzziness parameters in `create_search` to adjust match sensitivity. Your agent can then run `update_search_entities` to whitelist known safe entities based on your risk thresholds.

Your search history, PEP hits, and sanctions data pass straight between your local client and the ComplyAdvantage API via a secure V8 sandbox. Vinkius does not store your KYC payloads or screening logs.

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