How to Use the Gainsight PX MCP in LangChain

Q: How do I connect LangChain to the Gainsight PX MCP Server?

Install langchain-mcp-adapters and use MultiServerMCPClient. Pass your Vinkius endpoint URL and call client.gettools() to feed the tracking tools to your ReAct agent.

Q: Can my LangChain agent create new users in Gainsight PX?

Yes. The identifypxuser tool acts as an upsert. If the agent passes an email that doesn't exist, the system creates the profile automatically.

Q: How do I debug API limits when querying accounts?

Check your LangSmith traces. The verifyapiconnection tool will show you if the MCP connection is alive, but LangSmith reveals if your agent is stuck in a loop calling listpxaccounts.

Build multi-step reasoning pipelines with LangChain that pull Gainsight PX analytics straight into your agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gainsight PX MCP to LangChain

Create your Vinkius account to connect Gainsight PX 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 Gainsight PX with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Gainsight PX Events in LangChain

The `identify_px_user` tool pulls exact user profiles right into your LangChain context. Your ReAct agent reads the metadata, decides if the user fits a target segment, and immediately passes that ID down the chain. Next, the agent fires `track_server_event` to log custom milestones based on the previous step's output. LangSmith traces the entire sequence so you see exactly how many tokens it took to sync a profile and push an event.

Automate Account Health Checks

Calling `list_px_accounts` returns an array of companies matching your specific criteria. Your agent iterates through the list, piping each result into `get_account_details` to fetch granular usage metrics. You don't have to write manual loops. The framework handles the state, passing raw account data from the MCP Server into whatever downstream vector store or database you hooked up to the chain.

Map Feature Usage to Engagements

Running `list_product_features` grabs the exact tracking hierarchy you built in your product. The agent uses this dictionary to figure out which UI elements actually matter. From there, it calls `list_px_engagements` to see if your onboarding guides overlap with the features users ignore. You get a fully automated audit of your in-app messaging strategy without opening a dashboard.

Setup guide

Set up Gainsight PX 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 Gainsight PX 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({
    "gainsight-px-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 Gainsight PX 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 Gainsight PX. 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 Gainsight PX 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 Gainsight PX MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient`. Pass your Vinkius endpoint URL and call `client.get_tools()` to feed the tracking tools to your ReAct agent.

Yes. The `identify_px_user` tool acts as an upsert. If the agent passes an email that doesn't exist, the system creates the profile automatically.

You probably forgot to pass the required user ID. Agents sometimes guess parameters if you don't provide a strict prompt telling them to run `get_user_details` first.

Check your LangSmith traces. The `verify_api_connection` tool will show you if the MCP connection is alive, but LangSmith reveals if your agent is stuck in a loop calling `list_px_accounts`.

Your agent touches raw user metadata, including emails and engagement histories via `get_my_identity`. The Vinkius V8 Isolate Sandbox guarantees this data stays ephemeral in memory and vanishes the second your chain finishes executing.

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