How to Use the Shotstack MCP in LlamaIndex

Q: How do I query Shotstack's rendering capabilities using LlamaIndex?

You feed the output of rendervideo into your index. Later, you can ask questions about the rendered video content or status updates, and LlamaIndex will retrieve the relevant data points from the stored job IDs.

Q: Can I use the Shotstack MCP Server to check multiple sources with LlamaIndex?

Yes. You can run listingestedsources and index the results. This lets you combine document knowledge with API data, answering questions like 'Do we have a source for the campaign mentioned in this doc?'

Q: How does LlamaIndex help me manage Shotstack assets?

By indexing the output of listassetsfromrender or listhostedassets, you create a permanent knowledge graph. You can ask natural language questions about asset ownership or usage without executing another API call.

Q: If I build an RAG app with Shotstack and LlamaIndex, what's the process?

First, you run tools like listtemplates to get data. Then, you index that raw JSON output into your vector store. Finally, your application queries the knowledge base, which is grounded in the actual API data.

Index API results into knowledge with LlamaIndex, grounding your AI client in the Shotstack MCP Server data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shotstack MCP to LlamaIndex

Create your Vinkius account to connect Shotstack to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Shotstack with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Query render history from the MCP Server

`list_recent_renders` lets you query a searchable record of past video jobs. Instead of just running the tool, LlamaIndex indexes this output, so when you ask 'What did we make last week?', it grounds its answer in your actual `list_recent_renders` data. This means you can treat API history like corporate knowledge—it's searchable context for future decisions.

Search available video templates using LlamaIndex

Use the `list_templates` tool to get a list of all existing video blueprints. By indexing this output, you can ask semantic questions like 'Which template is best for social ads?' and LlamaIndex will search the descriptive text associated with each template. This saves you from having to manually review every single available video template.

Find specific assets by listing hosted files

`list_hosted_assets` provides a comprehensive list of all media stored on Shotstack. Indexing this output allows your RAG application to answer questions like, 'Where did we store the logo for Q2?' without needing direct API calls—it just searches the indexed data. It makes asset management part of the knowledge base.

Setup guide

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

You feed the output of `render_video` into your index. Later, you can ask questions about the rendered video content or status updates, and LlamaIndex will retrieve the relevant data points from the stored job IDs.

The server handles media assets and render metadata. When indexing this data via LlamaIndex, you are working with file paths, asset names, and status codes from tools like `get_render_status`.

Yes. You can run `list_ingested_sources` and index the results. This lets you combine document knowledge with API data, answering questions like 'Do we have a source for the campaign mentioned in this doc?'

By indexing the output of `list_assets_from_render` or `list_hosted_assets`, you create a permanent knowledge graph. You can ask natural language questions about asset ownership or usage without executing another API call.

First, you run tools like `list_templates` to get data. Then, you index that raw JSON output into your vector store. Finally, your application queries the knowledge base, which is grounded in the actual API 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