How to Use the Appcues MCP in LangChain

Q: How do I pass Appcues user profiles into a LangChain agent using MCP?

You use getuserprofile within your chain to fetch the profile JSON. The LangChain agent reads these attributes to decide the next step in your user onboarding sequence.

Q: Can a LangChain chain publish an Appcues flow autonomously?

Yes. By exposing publishflow to your LangChain agent, it can turn draft flows live when performance metrics meet your criteria.

Q: Which Appcues tools support mobile experiences?

Use listmobileexperiences to view your mobile-specific flows. Your agent can query this tool to separate desktop onboarding from your iOS or Android flows.

Q: Is my Appcues user profile data secure when using this server?

Yes. All user profiles and event payloads fetched via getuserprofile process locally in an isolated V8 sandbox. Vinkius never logs or stores the raw profile attributes passing through the endpoint.

Run multi-step Appcues onboarding flows and user profiling directly inside your LangChain loops with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Appcues MCP to LangChain

Create your Vinkius account to connect Appcues 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 Appcues with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Appcues Flow Deployments via LangChain

Let your LangChain agent audit and control your user onboarding states. The agent runs `list_flows` to see what is currently live, checks specific targets using `get_flow`, and decides to launch updates with `publish_flow` or pull back broken experiences using `unpublish_flow` based on real-time feedback. This isn't just a static script. Because it runs within a LangChain ReAct loop, the agent can inspect your runtime telemetry, notice a drop in conversion, and automatically switch out active walkthroughs without you writing hardcoded routing logic.

Trace Appcues Profile Updates in LangSmith

Monitor exactly how your agent handles user data. When the agent triggers `track_user_activity` or pulls target parameters with `get_user_profile`, LangSmith captures the exact payload, latency, and token cost of that specific step. You get a clear history of how your chains modify Appcues traits. If a user gets sorted into the wrong bucket, you can step through the execution graph to see exactly which tool argument caused the mismatch.

Dynamic Segment Targeting with this MCP Server

Combine external data with Appcues segment criteria. Your agent can read a database, compare it with `list_segments` and `get_segment`, and instantly determine if a user needs to be targeted with a new checklist via `list_checklists`. This setup bridges the gap between raw data warehouses and your product experience layer. By using this MCP Server, your LangChain chains act as the intelligent bridge, making real-time targeting decisions based on fresh user behaviors.

Setup guide

Set up Appcues 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 Appcues 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({
    "appcues-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 Appcues 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 Appcues. 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 Appcues 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 Appcues MCP in LangChain

You use `get_user_profile` within your chain to fetch the profile JSON. The LangChain agent reads these attributes to decide the next step in your user onboarding sequence.

Yes. By exposing `publish_flow` to your LangChain agent, it can turn draft flows live when performance metrics meet your criteria.

Use LangSmith to trace the inputs and outputs of tools like `track_user_activity`. Every schema validation error or API timeout shows up clearly in your trace timeline.

Use `list_mobile_experiences` to view your mobile-specific flows. Your agent can query this tool to separate desktop onboarding from your iOS or Android flows.

Yes. All user profiles and event payloads fetched via `get_user_profile` process locally in an isolated V8 sandbox. Vinkius never logs or stores the raw profile attributes passing through the endpoint.

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