How to Use the EX.CO Video Experience MCP in LlamaIndex

Q: How do I index EX.CO Video Experience MCP Server metadata into a LlamaIndex vector store?

You use the McpToolSpec to load tools like listvideolibrary into your LlamaIndex environment. The agent executes the tool, and you ingest the JSON output directly into your document store for indexing and semantic retrieval.

Q: How do I filter which EX.CO tools the LlamaIndex agent can access?

You use the allowedtools filter when setting up your McpToolSpec. This lets you restrict your agent to read-only tools like listvideoplaylists if you want to prevent configuration changes.

Index EX.CO video analytics and library metadata directly into LlamaIndex vector stores for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EX.CO Video Experience MCP to LlamaIndex

Create your Vinkius account to connect EX.CO Video Experience 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 EX.CO Video Experience with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable index of your EX.CO video library

The `list_video_library` tool retrieves your entire video catalog so your LlamaIndex pipeline indexes the metadata for semantic search. Your LlamaIndex agent queries this local index to find EX.CO videos matching specific topics or tags without calling the live API repeatedly. Once the agent finds the correct video, it uses `get_video_detailed_data` to pull specific configurations. This workflow keeps your live LlamaIndex queries fast and grounded in actual catalog data.

Ground RAG pipelines in live video analytics

Your LlamaIndex agent uses `get_video_analytics_summary` to pull real-time engagement data and inject it into your retrieval-augmented generation pipeline. This prevents your model from hallucinating EX.CO performance statistics when generating weekly reports. By combining this tool with `get_content_detailed_intelligence`, the LlamaIndex agent builds a complete picture of content health. LlamaIndex indexes the retrieved data on the fly, letting you ask natural language questions about video ROI.

Sync channel distribution data with this MCP Server

This MCP Server lets your LlamaIndex agent call `list_video_distribution_channels` to fetch active publishing pathways. The agent indexes these channels alongside your EX.CO content libraries to find distribution gaps. It then triggers `list_successfully_published_videos` to map which videos are live on which channels. You get an accurate, indexed map of your EX.CO reach that your LlamaIndex agent queries instantly.

Setup guide

Set up EX.CO Video Experience 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 EX.CO Video Experience 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 EX.CO Video Experience tools.",
)
response = await agent.run("List recent EX.CO Video Experience 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 EX.CO Video Experience. 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 EX.CO Video Experience 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 EX.CO Video Experience MCP in LlamaIndex

You use the McpToolSpec to load tools like `list_video_library` into your LlamaIndex environment. The agent executes the tool, and you ingest the JSON output directly into your document store for indexing and semantic retrieval.

Yes, because LlamaIndex indexes tool outputs, you query historical data retrieved by `get_video_analytics_summary` from previous agent runs. This lets you track performance trends over time without making redundant API calls.

Initialize the MCP client with your Vinkius endpoint, then convert it using McpToolSpec. You then pass these tools to your FunctionAgent to allow live data fetching during queries.

You use the allowed_tools filter when setting up your McpToolSpec. This lets you restrict your agent to read-only tools like `list_video_playlists` if you want to prevent configuration changes.

Yes, your account metadata and credentials are sandboxed inside isolated V8 execution environments. No data is stored or cached on the Vinkius platform, ensuring your EX.CO integration remains strictly private and compliant with your local security policies.

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