How to Use the Brightcove MCP in LlamaIndex

Q: How does LlamaIndex index metadata from my Brightcove account?

The framework uses the McpToolSpec to call listvideos and ingest the resulting JSON. LlamaIndex then parses these video records into text chunks and embeds them into your vector database.

Q: Can I use LlamaIndex to update Brightcove video metadata?

Yes, your agent can use the updatevideo tool based on its index queries. If the vector search reveals a video with missing tags, the agent triggers the update tool to patch the metadata in Brightcove.

Q: Does this MCP Server support LlamaIndex query engines?

It integrates directly. You can register tools like getplaylist as functional tools within a LlamaIndex FunctionAgent to let your query engine fetch live video data on demand.

Q: Can I restrict which Brightcove tools LlamaIndex can access?

You can use the allowedtools filter during initialization to restrict access to the MCP tools. For example, you can expose listvideos while blocking destructive tools like deletevideo entirely.

Index your Brightcove video metadata into LlamaIndex vector stores to build semantic search engines for your entire media library.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brightcove MCP to LlamaIndex

Create your Vinkius account to connect Brightcove 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 Brightcove with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Brightcove video data via MCP Server into LlamaIndex

The `list_videos` tool pulls raw metadata from your video cloud account so your LlamaIndex pipeline can index it. Your agent parses the descriptions, tags, and custom fields, converting them into searchable document nodes. This setup lets you run semantic queries over your video library instead of relying on basic keyword matching. The agent queries the index first, then uses `get_video` to fetch the complete, live metadata for the matching asset.

Query playlist structures semantically

The `list_playlists` tool retrieves your current playlist configurations directly into your index. LlamaIndex stores these structures as nodes, mapping which videos belong to which collections. When you ask your agent which playlist needs updating, it searches the vector store and calls `get_playlist` to verify the live state. You get answers grounded in your actual Brightcove configurations, preventing hallucinated playlist references.

Audit folder contents through vector search

The `list_folders` tool extracts your directory hierarchy, allowing LlamaIndex to build a semantic map of your storage setup. Your agent analyzes this structure to find organization gaps. By executing `get_folder_videos`, the agent checks the contents of specific folders and indexes the video details. This lets you query your directory contents using natural language queries instead of clicking through the Brightcove console.

Setup guide

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

The framework uses the `McpToolSpec` to call `list_videos` and ingest the resulting JSON. LlamaIndex then parses these video records into text chunks and embeds them into your vector database.

Yes, your agent can use the `update_video` tool based on its index queries. If the vector search reveals a video with missing tags, the agent triggers the update tool to patch the metadata in Brightcove.

It integrates directly. You can register tools like `get_playlist` as functional tools within a LlamaIndex `FunctionAgent` to let your query engine fetch live video data on demand.

You can use the `allowed_tools` filter during initialization to restrict access to the MCP tools. For example, you can expose `list_videos` while blocking destructive tools like `delete_video` entirely.

Your Brightcove credentials and folder names are processed entirely in memory within an ephemeral V8 sandbox. Vinkius never logs the actual payload content of your `list_folders` or `get_folder_videos` execution.

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