How to Use the FileStack MCP in Google ADK

Q: How do I run FileStack OCR inside a Google ADK agent?

You call getocr through the FileStack MCP toolset. This returns the extracted text directly to your Google ADK agent, which can then analyze or store it.

Q: Can my Google ADK agent handle video transcoding via FileStack?

Yes, your agent calls startvideotranscode to trigger the job. The Google ADK agent then uses getvideostatus to check when the transcoded file is ready.

Q: How do I restrict which tools are exposed?

You can use the toolnames filter when initializing your McpToolset. This lets you expose only specific tools like uploadfromurl or getmetadata to your agent.

Q: What is the best way to connect FileStack to Google ADK?

Use the McpToolset class with your Vinkius HTTP endpoint URL. This registers the FileStack MCP Server tools directly into your Google ADK agent's tool library.

Process massive media files and extract OCR text for your Google ADK enterprise agents.

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 Google ADK

Create your Vinkius account to connect FileStack to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise media ingestion with Google ADK

Feed your Gemini long-context models by using `upload_from_url` to ingest large files directly into your FileStack storage via this MCP Server. This keeps your Google ADK agent from choking on raw file downloads and keeps memory usage low. Once stored, the agent calls `get_metadata` to extract file properties and EXIF data. This structured metadata can be piped straight into BigQuery to track your media pipeline's performance over time.

Structured vision data for Gemini models

Gemini models excel at reasoning when you run `get_image_tags` and `get_ocr` to turn visual assets into clean text. This MCP Server lets your agent run those tools to turn images and documents into structured text. By feeding this extracted text directly into the Google ADK context window, you avoid sending massive image files to the LLM. You save on token costs while keeping your agent's reasoning highly accurate.

Safe asynchronous video processing

Handle heavy video workloads by starting a transcode job with `start_video_transcode` from your agent. The Google ADK agent polls `get_video_status` asynchronously, allowing it to perform other tasks while the video processes. For content moderation, the agent runs `get_sfw_status` to flag inappropriate uploads before they reach your enterprise database. You can then use `generate_transform_url` to serve safe, resized versions of the media.

Setup guide

Set up FileStack MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with FileStack tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="FileStack_agent",
    model="gemini-2.0-flash",
    instruction="You have access to FileStack tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You call `get_ocr` through the FileStack MCP toolset. This returns the extracted text directly to your Google ADK agent, which can then analyze or store it.

Yes, your agent calls `start_video_transcode` to trigger the job. The Google ADK agent then uses `get_video_status` to check when the transcoded file is ready.

You can use the `tool_names` filter when initializing your `McpToolset`. This lets you expose only specific tools like `upload_from_url` or `get_metadata` to your agent.

Use the `McpToolset` class with your Vinkius HTTP endpoint URL. This registers the FileStack MCP Server tools directly into your Google ADK agent's tool library.

Yes, the server runs in an ephemeral, zero-trust sandbox. Your file metadata, OCR text, and image tags are transmitted securely to your agent and are never cached or logged by the MCP host.

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