How to Use the FileStack MCP in LangChain

Chain FileStack media processing tools directly into your LangChain agents to automate image analysis and video transcoding pipelines.

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 LangChain

Create your Vinkius account to connect FileStack to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LangChain chains with FileStack ingestion

`upload_from_url` acts as the entry point for your LangChain document processing chains using the FileStack MCP Server. Your agent pulls remote assets and immediately passes the resulting handle to downstream tools without manual intervention. Once ingested, the agent uses `get_metadata` to inspect file properties or runs `get_ocr` to extract raw text. LangSmith traces each step, showing you exact execution times and payload sizes for every file processed in the chain.

Dynamic asset transformation via LangChain agents

`generate_transform_url` builds target-specific image URLs based on real-time decisions made by your LangChain agent connected to this MCP server. The agent analyzes the user's request, determines the required dimensions, and generates the precise transformation string. Because this tool returns a URL instead of processing the image on your local compute, your chain stays lightweight. The agent passes this URL to subsequent prompts or external APIs, keeping memory usage flat even when handling thousands of assets.

Manage long-running transcodes in LangChain

`start_video_transcode` initiates asynchronous encoding jobs directly from an agent's reasoning loop. The agent triggers the process, receives a UUID, and schedules polling tasks without blocking other chain operations. The agent uses `get_video_status` to check the progress of the transcode job. This lets your LangChain application pause, yield control, or run parallel chains until the transcode completes, preventing timeout errors on large video files.

Setup guide

Set up FileStack MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes FileStack tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "filestack-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent FileStack transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the MCP server URL. Call client.get_tools() to retrieve the FileStack tools and pass them directly to your agent constructor.

Yes, LangChain excels at sequential tool execution. The agent calls upload_from_url to ingest the file, and then passes the resulting file handle directly into get_ocr to extract text in a single run.

LangSmith logs every MCP tool call, showing you the exact inputs sent to get_image_tags or get_sfw_status. You can inspect latency, verify payload structures, and trace failures when your agent evaluates image safety.

This tool only constructs the URL pattern to save execution costs and bandwidth. Your LangChain agent receives the structured URL string, which it can then pass directly to frontend clients or other steps in your pipeline.

FileStack processes your uploaded files, images, and OCR text on its secure cloud infrastructure. The MCP server acts as a stateless gateway, passing your API key and file handles securely without storing any content locally.

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