How to Use the FusionSignage MCP in LlamaIndex

Q: How can LlamaIndex index the output from FusionSignage tools?

When you use the McpToolSpec, the output of any tool call, like listplaylists, is automatically captured. LlamaIndex then ingests this data into your configured vector index, making it available for semantic queries.

Q: How do I get the tool list from the FusionSignage MCP server for LlamaIndex?

After creating a BasicMCPClient with your Vinkius URL, you instantiate McpToolSpec with that client. The totoollistasync() method then provides the tools formatted for a LlamaIndex agent.

Turn your signage network into a queryable knowledge base with LlamaIndex. Ask questions about playlists, media, and screen status in plain English.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FusionSignage MCP to LlamaIndex

Create your Vinkius account to connect FusionSignage 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 FusionSignage with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Your Live Signage Configuration

LlamaIndex doesn't just call tools; it remembers the answers. Every time your agent calls `list_playlists` or `get_media_item`, the results are indexed into a vector store. You can then ask your agent, "which playlists are using the 'spring_sale.mp4' video?" and get an answer grounded in your network's actual state. This creates a living document of your entire deployment. Query past states, analyze content assignments with `get_playlist`, and audit schedules without digging through logs. Your RAG application can use `list_screens` and `get_screen` to build a complete snapshot, ready for your questions.

RAG-Powered Content Management with LlamaIndex

Combine live data from this MCP Server with your own documents. Your agent can read a marketing brief you've provided, then use the FusionSignage tools to find the right assets with `list_media` and assemble a new playlist with `create_playlist`. The agent uses your documents for context and the MCP tools for action. It's a practical way to ground your agent's work in both your strategic goals and the real-time status of your signage network.

Build an Intelligent Troubleshooting Bot

Construct a troubleshooting agent that knows your network's history. When a user reports a problem, the agent can query its index of past `get_screen_status` calls to look for recurring patterns on that specific device. It can then use live tool calls like `check_fusion_status` to verify the current state. Based on both historical and live data, it can recommend a fix, like using `update_screen` with a known-good configuration from a similar, healthy screen. This is the power of a LlamaIndex-aware MCP Server.

Setup guide

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

When you use the `McpToolSpec`, the output of any tool call, like `list_playlists`, is automatically captured. LlamaIndex then ingests this data into your configured vector index, making it available for semantic queries.

Absolutely. You can feed your marketing plans or content briefs into the index. The agent will use that context along with live tool calls like `list_media` and `create_playlist` to build and manage your content.

A script just executes commands. LlamaIndex builds a knowledge base from the results, allowing you to ask natural language questions about your network's configuration and history. The MCP server provides the live data for this knowledge base.

After creating a `BasicMCPClient` with your Vinkius URL, you instantiate `McpToolSpec` with that client. The `to_tool_list_async()` method then provides the tools formatted for a LlamaIndex agent.

The tool outputs, which include details on your media, playlists, and screens, are stored in the vector index you configure for LlamaIndex. The Vinkius MCP server itself is stateless; it only processes requests and doesn't hold your 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