How to Use the Appcues MCP in LlamaIndex

Q: How does LlamaIndex index live Appcues flows using this MCP Server?

The framework uses this server to run listflows and ingest the raw JSON configurations. These configurations are then chunked and stored in your vector database for semantic search.

Q: Can I query Appcues segment criteria using LlamaIndex?

Yes. By calling getsegment through the tool spec, LlamaIndex indexes the rules of your cohorts, allowing you to ask natural language questions about who qualifies for each group.

Q: How does LlamaIndex handle Appcues mobile experience data via MCP?

The agent calls listmobileexperiences to pull your mobile flow configurations, which are then indexed alongside your desktop flows to provide unified search results.

Q: Can I use this server to update user traits?

Yes. You can run trackuseractivity to send real-time profile updates and events back to your Appcues account based on query results.

Q: How does this MCP Server secure my indexed Appcues flow configurations?

Your flow configurations and segment rules retrieved by getflow are stored in your local vector store. The connection runs through an ephemeral, zero-trust V8 sandbox that never caches your Appcues API keys or payload data.

Index your Appcues flows and segments into LlamaIndex to query your product experiences with RAG.

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 LlamaIndex

Create your Vinkius account to connect Appcues to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build an Active RAG Index of Appcues Flows

Stop guessing what is live in your product. Use `list_flows` and `get_flow` to pull your entire onboarding library, then index those configurations straight into your vector store using LlamaIndex. Your agent can then query this index to answer complex questions about your current setup. Instead of clicking through the UI, ask your LLM which flows target new signups and get answers grounded in real API data.

Semantic Search Over Appcues Segments

Feed your user cohort definitions directly into your knowledge base. By pulling segment criteria with `list_segments` and `get_segment`, LlamaIndex stores the exact rules defining your active user groups. When you need to design a new campaign, query your index to see if an overlapping segment already exists. This prevents duplicate targeting rules and keeps your user experience clean.

Context-Aware User Activity Logging via MCP Server

Turn live user actions into searchable history. By feeding `track_user_activity` events into your LlamaIndex pipeline, you build a chronological, queryable timeline of how users interact with your product. When diagnosing an issue, the agent pulls the user profile via `get_user_profile` and combines it with indexed activity logs to give you a complete, context-rich summary of the user's path.

Setup guide

Set up Appcues MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Appcues MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Appcues tools.",
)
response = await agent.run("List recent Appcues data")

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 LlamaIndex

The framework uses this server to run `list_flows` and ingest the raw JSON configurations. These configurations are then chunked and stored in your vector database for semantic search.

Yes. By calling `get_segment` through the tool spec, LlamaIndex indexes the rules of your cohorts, allowing you to ask natural language questions about who qualifies for each group.

The agent calls `list_mobile_experiences` to pull your mobile flow configurations, which are then indexed alongside your desktop flows to provide unified search results.

Yes. You can run `track_user_activity` to send real-time profile updates and events back to your Appcues account based on query results.

Your flow configurations and segment rules retrieved by `get_flow` are stored in your local vector store. The connection runs through an ephemeral, zero-trust V8 sandbox that never caches your Appcues API keys or payload 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