How to Use the Flowcode MCP in LlamaIndex

Q: How do I index my Flowcode scan history into a LlamaIndex vector store?

You fetch the log using getrecentscans and pass the raw data to a LlamaIndex Document object. The framework then embeds and stores this text for semantic search.

Q: Can I build a LlamaIndex RAG application that queries Flowcode campaign performance?

Yes, you can. By indexing outputs from listcampaigns and listconversionrates, your LlamaIndex agent can answer complex questions about your physical marketing ROI.

Q: How does this Flowcode MCP Server handle large directories of assets in LlamaIndex?

The server uses listfolders and listflowcodes to retrieve your entire asset directory. LlamaIndex indexes these lists so your agent can quickly locate any code without hitting API rate limits.

Q: Where is my Flowcode geographic scan data stored during LlamaIndex queries?

Geographic data from getgeographicanalytics is processed entirely in memory or stored in your local vector database. Vinkius operates a zero-trust sandbox for this MCP Server that never caches or inspects your location logs.

Index live QR scan data and Flowpage interactions into your LlamaIndex vector store for instant, grounded RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowcode MCP to LlamaIndex

Create your Vinkius account to connect Flowcode 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 Flowcode with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Real-Time QR Scan Logs for RAG

The `get_recent_scans` tool fetches raw activity logs so your LlamaIndex pipeline can convert physical scan events into searchable vector embeddings. This MCP connection prevents your agent from hallucinating performance numbers by grounding its answers in actual, time-stamped scan history. You query your index to find patterns in user behavior without running manual SQL queries. The agent pulls the logged events, indexes them, and answers questions about peak scan times instantly.

Query Flowpage Performance inside LlamaIndex

The `get_flowpage_analytics` tool retrieves landing page events directly into your indexer. LlamaIndex stores these interaction metrics alongside your physical scan data, building a unified knowledge base of your offline-to-online funnel. This integration lets you ask your agent which dynamic landing pages are driving the most conversions. The agent queries the vector store, compares historical events, and returns grounded recommendations.

Retrieve Folders and Asset Metadata

The `list_folders` tool exposes your asset organization structure to your LlamaIndex agent. This lets the agent map where specific dynamic codes live, making it easy to retrieve and categorize assets during RAG-driven audits. Instead of searching through a web UI, you ask your agent where a specific campaign asset is stored. The agent searches the indexed folder metadata and returns the exact location.

Setup guide

Set up Flowcode 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 Flowcode 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 Flowcode tools.",
)
response = await agent.run("List recent Flowcode 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 Flowcode. 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 Flowcode 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 Flowcode MCP in LlamaIndex

You fetch the log using `get_recent_scans` and pass the raw data to a LlamaIndex Document object. The framework then embeds and stores this text for semantic search.

Yes, you can. By indexing outputs from `list_campaigns` and `list_conversion_rates`, your LlamaIndex agent can answer complex questions about your physical marketing ROI.

The server uses `list_folders` and `list_flowcodes` to retrieve your entire asset directory. LlamaIndex indexes these lists so your agent can quickly locate any code without hitting API rate limits.

Yes, you configure this during client initialization. You can restrict the agent to read-only tools like `get_audience_summary` and block creation tools like `create_flowcode` on the MCP Server.

Geographic data from `get_geographic_analytics` is processed entirely in memory or stored in your local vector database. Vinkius operates a zero-trust sandbox for this MCP Server that never caches or inspects your location logs.

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