How to Use the FileStack MCP in LlamaIndex

Q: Can LlamaIndex index the output of FileStack getimagetags?

Yes, LlamaIndex captures the JSON output from getimagetags and converts it into metadata attributes. This lets you run semantic searches that filter images based on detected objects and visual features.

Q: How does FileStack help LlamaIndex handle scanned PDFs?

Your agent uses getocr to extract text from scanned PDFs. LlamaIndex then parses this text into chunks, embeds them, and inserts them into your vector index for retrieval during user queries.

Q: Does the LlamaIndex integration support asynchronous video transcoding?

Yes, the agent can call startvideotranscode to begin processing and poll the status using getvideostatus. The resulting video metadata can then be indexed to document the completed transcode.

Index FileStack file metadata and OCR text directly into LlamaIndex vector stores to build searchable media knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FileStack MCP to LlamaIndex

Create your Vinkius account to connect FileStack 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 FileStack with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn FileStack OCR data into LlamaIndex nodes

`get_ocr` extracts text from scanned documents and receipts, which your LlamaIndex pipeline instantly converts into document nodes via the MCP Server. The framework indexes these nodes into your vector store, making raw image content searchable via semantic queries. Your agent uses `get_image_tags` alongside the text extraction to add rich metadata tags to each indexed node. This dual-source indexing ensures that both visual elements and written text are fully queryable within your RAG application.

Filter LlamaIndex queries using FileStack metadata

`get_metadata` retrieves file sizes, mime types, and creation dates to populate LlamaIndex metadata fields using this MCP integration. This structural data allows your query engine to apply strict SQL-like filters before performing vector searches on your files. By combining this structured metadata with content filters like `get_sfw_status`, your agent ensures that unsafe or irrelevant files are automatically excluded from RAG retrieval loops, protecting the integrity of your generation step.

Ingest files into LlamaIndex using FileStack

`upload_from_url` retrieves remote files and adds them to your LlamaIndex data ingestion pipeline on the fly. When a user submits a URL, the agent uploads it, extracts metadata, and indexes the content without leaving the session. This dynamic ingestion loop uses `generate_transform_url` to resize or format images before they are passed to multimodal embedding models. It optimizes processing speeds and keeps vector store storage requirements predictable.

Setup guide

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

Initialize the BasicMCPClient with the server URL and wrap it in McpToolSpec. Call to_tool_list_async() to convert the FileStack capabilities into standard LlamaIndex tools for your agent.

Yes, LlamaIndex captures the JSON output from get_image_tags and converts it into metadata attributes. This lets you run semantic searches that filter images based on detected objects and visual features.

Your agent uses get_ocr to extract text from scanned PDFs. LlamaIndex then parses this text into chunks, embeds them, and inserts them into your vector index for retrieval during user queries.

Yes, the agent can call start_video_transcode to begin processing and poll the status using get_video_status. The resulting video metadata can then be indexed to document the completed transcode.

The FileStack MCP Server processes and extracts text from your images and documents using encrypted HTTPS connections. LlamaIndex only stores the extracted text and metadata in your local or cloud vector database, keeping the original assets secure.

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