How to Use the OpenPanel MCP in LangChain

Q: How do I handle user sessions when combining OpenPanel and LangChain?

You should run identifyuser at the start of your LangChain run to bind the current session to a specific user ID. If your agent runs in a stateless environment, you can pass the user ID as a constant parameter in your tool calls. This prevents anonymous event bloat and keeps your user profiles clean.

Feed real-time telemetry straight from your LangChain decision loops into OpenPanel without writing tracking boilerplate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OpenPanel MCP to LangChain

Create your Vinkius account to connect OpenPanel 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 OpenPanel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Trace LangChain agent actions inside OpenPanel

When your LangChain agent decides to run a tool, you need to know about it instantly inside OpenPanel. This MCP Server lets your LangChain agent call `track_event` directly inside its active execution chain. The output of one LangChain step feeds directly into your OpenPanel analytics, letting you log agent decisions, user prompts, and execution paths without manual instrumentation. You can monitor these telemetry pipelines using LangSmith to verify that your OpenPanel payloads match your token usage metrics.

Update OpenPanel user profiles dynamically across LangChain

LangChain pipelines excel at multi-step reasoning, and now they can update OpenPanel user profiles on the fly. Your LangChain agent can use `identify_user` to tie a specific chain session to a real user record as soon as the authentication step resolves. As the LangChain agent progresses through a task, it can adjust OpenPanel traits in real-time. It uses `increment_property` or `decrement_property` to modify numeric values like total queries run or remaining credits inside your user profile.

State-driven OpenPanel routing in LangGraph

You can build LangGraph agents that route messages based on the user's current OpenPanel state. The LangChain agent checks user traits, processes a prompt, and then uses `track_event` to log the outcome. Because this runs over an MCP connection, you don't need to configure OpenPanel SDKs for every single node in your LangGraph. The LangChain agent treats telemetry as a native tool, invoking it only when the chain logic dictates.

Setup guide

Set up OpenPanel 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 OpenPanel 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({
    "openpanel-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 OpenPanel 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 OpenPanel. 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 OpenPanel 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 OpenPanel MCP in LangChain

Your LangChain agent treats OpenPanel as a toolset within its ReAct loop. It can call `track_event` or `identify_user` just like any database tool. The adapter converts these calls into direct API requests, feeding your product metrics in real-time.

Yes, you can pass token metrics directly into the event properties. When your agent runs `track_event`, it can include the token count from your LangChain callback handler. This lets you monitor the exact cost of every user interaction inside your analytics dashboard.

You should run `identify_user` at the start of your LangChain run to bind the current session to a specific user ID. If your agent runs in a stateless environment, you can pass the user ID as a constant parameter in your tool calls. This prevents anonymous event bloat and keeps your user profiles clean.

Every tool call made to the server is fully visible inside LangSmith. You can inspect the exact payload sent by `track_event` or `increment_property` to debug formatting errors. This makes it easy to spot where your agent is passing malformed telemetry data.

This server acts as a direct pipeline for your user IDs and custom event properties. It never caches or stores this data locally. Every telemetry payload is sent straight to OpenPanel over an encrypted connection, ensuring your users' tracking data remains completely private.

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