How to Use the CaptionHub MCP in LlamaIndex

Q: Can I filter CaptionHub tools in LlamaIndex?

Use the allowedtools filter during setup to restrict which parts of the CaptionHub API your agent can access. This keeps your agent focused on specific tasks like listing or updating.

Index your video localization knowledge in LlamaIndex by pulling data through the CaptionHub MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CaptionHub MCP to LlamaIndex

Create your Vinkius account to connect CaptionHub 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 CaptionHub with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index CaptionHub data with LlamaIndex

Convert project metadata into a searchable knowledge base. By calling `list_projects`, you feed the raw list into your vector store, allowing the agent to answer questions about your entire library. This makes past project configurations queryable. Stop guessing which project ID belongs to which video and let the index find it for you.

Ground your agent in real project data

Use `get_project_details` to pull specific information into your RAG pipeline. The agent retrieves the current state of any project, preventing hallucinations about caption status or language support. Combine this with local documents to provide a complete picture. Your agent knows both your internal guidelines and the live status of every video.

Manage project updates via tool execution

Update project metadata using `update_project` while maintaining the index. If you change a title or language, the agent performs the action and refreshes the context. Everything stays in sync. The agent performs the work and then queries the updated index to verify the changes took effect.

Setup guide

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

Use the MCP tool spec to convert the server tools into a format LlamaIndex understands. Once initialized, you can call the tools and store the results in your index for future semantic search.

The server provides the data, and your index stores it. As long as you run the tool to fetch project details, that information becomes part of your searchable knowledge base.

Use the allowed_tools filter during setup to restrict which parts of the CaptionHub API your agent can access. This keeps your agent focused on specific tasks like listing or updating.

Yes, once you pass the tool outputs into your indexer, the results behave like any other document. You can perform natural language queries to find specific projects or status updates.

Data is transmitted via a secure, token-authenticated connection. Only the specific transcript text and project metadata you query are ever indexed into your vector store.

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