How to Use the Openli MCP in LangChain

Build LangChain pipelines that pull Openli compliance data and update privacy agreements on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Openli MCP to LangChain

Create your Vinkius account to connect Openli to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Openli with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate multi-step compliance workflows

Your LangChain agents can now check your regulatory standing and update documents in a single, unbroken chain. When a user changes their cookie preferences, the agent triggers `save_consent` and immediately updates the central registry without manual intervention. You get a clear, step-by-step execution path that handles legal requirements programmatically. By combining this MCP Server with LangSmith, you trace every legal decision your agent makes. If a client disputes their agreement status, this lets you look up the exact chain run that executed `get_agreement` to prove when and how the terms were presented.

Handle data subject requests programmatically

Stop manually sorting through privacy requests. This integration lets your LangChain chains handle the heavy lifting by pulling incoming requests directly into your backend. An agent can call `list_dsars` to fetch pending requests, analyze the payload, and then execute `create_dsar` to log a new entry in your compliance database. The agent evaluates the request type and decides which tool to run next based on the output of the previous step. You don't have to write custom glue code to connect your database to your privacy desk anymore.

Audit third-party vendor access

Keep your vendor list updated without constantly auditing your codebase. Your agent can run `list_vendors` to retrieve your current third-party list and compare it against your active software dependencies. If it finds a mismatch, it uses `get_vendor` to inspect the details and flags the discrepancy for your legal team. This keeps your public-facing disclosures accurate. You run this as a scheduled LangChain runnable that keeps your external documentation perfectly aligned with your actual data practices.

Setup guide

Set up Openli 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 Openli 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({
    "openli-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 Openli 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 Openli. 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 Openli 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 Openli MCP in LangChain

You initialize the server connection using the LangChain MCP adapter in your setup file. Once connected, you call `client.get_tools()` to retrieve the toolset and pass them directly to your ReAct agent. This exposes operations like `check_openli_status` to your agent immediately.

Yes, you can track every tool call using LangSmith observability. Every time your agent runs `get_consent` or updates an agreement, the inputs and outputs are logged in your trace history. This gives you a clear audit trail of your automated compliance decisions.

You build multi-step chains where the output of one tool determines the next action. For example, your agent can run `list_agreements` to find outdated policies, then chain that output into `create_agreement` to generate a fresh version. The entire sequence runs autonomously based on your logic.

No, the adapter handles the schema translation automatically. Your LangChain agent interacts with tools like `list_audit_logs` as if they were native Python or TypeScript functions. You focus on building the logic while the protocol manages the communication.

Your user consent records and audit logs are transmitted securely through the V8 sandbox directly to your client. No third-party servers store the raw payloads of your `save_consent` or `list_consents` calls. You maintain complete control over the transit of your compliance data.

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