UPYUN Developer Platform MCP for AI. Manage assets, deploy code, and audit storage capacity.

Q: How do I check how much storage I'm using with getserviceusage?

getserviceusage reports your current consumption against your total bucket limit. It gives a summary metric, telling you exactly what percentage of your allotted space is used.

Q: Can I use listdirectory to see files inside subfolders?

Yes, listdirectory reads the contents of a specified path. You can point it at a folder like /images/assets/ to list everything within that subdirectory.

Q: What should I use if I need to add a new asset? Should I use createtextfile?

Yep, createtextfile is the tool for uploading assets. You give it the file path and the content string, and it handles writing the text data directly to your bucket.

Q: Is there a specific way to check if a file exists using getfileinfo?

Running getfileinfo on a specific path will confirm existence. If the file isn't found, the tool returns an error, which your agent uses to let you know it's missing.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

UPYUN Developer Platform MCP Server gives your AI agent direct API access to UPYUN's CDN and cloud storage buckets. You can manage files, list directories, create new assets, and check service capacity without using any command-line tools or local SDKs.

It lets your agent interact with your entire file system like a native developer would.

What your AI can do

Create text file

Creates and uploads a plain text file to UPYUN's cloud storage bucket.

Delete file

Deletes any specified file from your UPYUN cloud buckets.

Get file info

Retrieves metadata (like size or modification date) for a specific UPYUN file path.

+ 2 more capabilities included

List Directory Contents

The agent lists all files and folders within a specified UPYUN directory path.

Create Text Files

The agent writes and uploads new text files directly into your UPYUN bucket.

Delete Files

The agent removes specified files from any location within the UPYUN bucket structure.

Get File Metadata

The agent retrieves specific details, like size and last modified date, for a single file.

Check Service Usage

The agent fetches usage statistics to report on how much storage you've consumed in your UPYUN bucket.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

UPYUN Developer Platform: 5 Tools for Cloud Operations

Use these five tools to allow your agent full control over file system actions—from creating new assets to auditing service usage across UPYUN buckets.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using UPYUN Developer Platform on Vinkius

Create Text File

Creates and uploads a plain text file to UPYUN's cloud storage bucket.

Delete File

Deletes any specified file from your UPYUN cloud buckets.

Get File Info

Retrieves metadata (like size or modification date) for a specific UPYUN file path.

Get Service Usage

Fetches and reports the overall storage usage metrics for your entire UPYUN bucket...

List Directory

Lists all files and subfolders contained within a specified UPYUN directory path.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The UPYUN Developer Platform integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "upyun-developer-platform": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the UPYUN Developer Platform tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"upyun-developer-platform": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with UPYUN Developer Platform, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

UPYUN Developer Platform MCP server cover

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by UPYUN. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 5 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manually managing cloud assets feels like running a dozen different CLI commands.

Today, updating an asset means logging into the web console or setting up a local build script. You have to click through folders, copy out file paths, and then run separate delete or upload commands for every single item. It’s slow, error-prone, and you're always worried about deleting the wrong thing.

With this MCP server, your agent handles it all in natural language. Need to list everything? Just ask. Need to deploy a patch? The agent runs `create_text_file` and gets the asset live. You just get the result—the change is made.

The UPYUN Developer Platform MCP Server: File & Bucket Operations

Forget writing complex Python scripts that handle authentication, file paths, and error checking. You never have to worry about the HMAC-SHA1 header generation again.

The agent manages all those low-level details for you. It’s just clean access: you tell it to list a directory, and it returns the contents. Done.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Yo, this UPYUN Developer Platform MCP Server hooks up your AI agent straight to UPYUN's CDN and cloud storage buckets. You don't need any command-line crap or local SDKs; your agent can treat your whole file system like it's running on a native dev machine. It gives you direct API access, so you can manage files, build assets, list directories, delete stuff, and check service capacity—all without leaving your AI client.

Managing Your Files
Your agent handles all the heavy lifting when it comes to file operations. You'll use list_directory to pull a full manifest of every file and subfolder within any specified UPYUN directory path, letting you see exactly what's hanging out there. Need to drop new content? Just call create_text_file, and your agent uploads a plain text file right into the cloud storage bucket for you.

When you’re done with something, remember that delete_file lets your agent wipe any specified file from anywhere in the UPYUN bucket structure.

Getting File Details and Usage Stats
The server gives you visibility on what's going on under the hood. You can check the specifics of a single file using get_file_info; this retrieves metadata like its size or when it was last modified. And if you need to know how much storage space you’ve burned through, just run get_service_usage.

That pulls and reports the overall usage metrics for your entire UPYUN bucket service.

How It Works
It's straightforward: Your agent connects to this server on Vinkius. When it needs to perform any of these actions—like listing a folder or creating a file—it sends the request through the MCP, and we handle the complex API auth behind the scenes. This keeps your credentials safe while giving you that full-blast control over your assets.

Built · Hosted · Managed by Vinkius UPYUN Developer Platform MCP Server - Cloud File Management

Server ID 019d8496-754e-70d3-b515-842ab43ad972

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Who is this actually for?

This is for DevOps engineers who are sick of writing boilerplate deployment scripts. It’s also useful for frontend devs prototyping sites or content admins needing quick asset checks without logging into a dashboard. If your job involves managing assets across cloud storage, this saves hours.

DevOps Engineer

Automates static site generation and deployments by pushing file changes directly to UPYUN instances using tools like create_text_file.

Frontend Developer

Prototyping web apps without writing complex deployment scripts; they use the agent to deploy files instantly via the MCP.

Content Administrator

Quickly checks what assets are in specific directories—like verifying if a logo file exists—using list_directory via natural language prompts.

What Changes When You Connect

Stop writing deployment scripts. Your agent can use create_text_file to deploy new static content or updated HTML files directly to your CDN domains.

Need a quick asset check? Use the list_directory tool to see everything in a bucket's root path just by asking, avoiding manual navigation through a web console.

Track costs and capacity easily. The get_service_usage tool gives you real-time storage metrics so you know exactly when you hit your consumption limits.

Need to clean up old assets? Use delete_file with natural language prompts to remove junk files without needing to manually specify every single file path.

Get details on any asset instantly. Run get_file_info to check a file's size or last modified date before relying on it for production code.

See it in action

01 01

A new page needs assets uploaded and checked.

The content team writes a new landing page. They ask their agent to first run list_directory to check if the 'images' folder exists. If it does, they ask the agent to use create_text_file to upload the new CSS file, and finally, they use get_file_info on that new file to confirm its size.

02 02

The site is running low on space.

A DevOps engineer notices potential billing issues. They prompt their agent with a request for 'current storage usage.' The agent immediately calls get_service_usage and reports the bucket's remaining capacity, preventing overspending.

03 03

Old development assets need to be purged.

A developer finishes a project branch. Instead of manually logging in and deleting files, they instruct their agent: 'Delete all temporary JS files from the /temp/ directory.' The agent executes delete_file across the whole group.

04 04

Deploying a quick patch requires a new file.

The frontend team needs to test an emergency fix. They ask their agent to create a placeholder file: 'Create /hotfix.html with content

Test

.' The agent executes create_text_file, and the changes are live on the CDN.

The honest tradeoffs

Assuming listing shows everything.

Anti-pattern

User asks: 'Show me all assets in my bucket.' They assume they get file contents, but list_directory only gives them paths and folder names. This leads to follow-up prompts that waste time.

The Fix

Trying to delete a directory.

Anti-pattern

delete_file is for individual files; it won't work on folders, even if you give it the path to a full folder. You have to target every file inside manually or via scripting.

The Fix

Over-relying only on `get_file_info`.

Anti-pattern

If you only run get_file_info repeatedly, you get metadata but never see the full structure. You'll end up calling it dozens of times when a single list_directory call would have given you the map first.

The Fix

Ignoring service limits.

Anti-pattern

Deploying large numbers of files without checking capacity leads to rate limiting or billing surprises. Always check with get_service_usage first.

The Fix

When It Fits, When It Doesn't

Use this server if your workflow requires managing physical assets (files, folders) and tracking usage metrics on a cloud CDN like UPYUN. Specifically, use it when you need an AI agent to execute file system primitives: listing (list_directory), creating (create_text_file), deleting (delete_file), or checking status (get_file_info).

Don't use this if your problem is purely about data transformation (e.g., converting JSON to XML) or complex business logic that doesn't touch the file system itself. For usage reporting, get_service_usage is specific; don’t try to get billing reports via list_directory. Stick to these boundaries for predictable results.

Questions you might have

How do I check how much storage I'm using with `get_service_usage`? +

get_service_usage reports your current consumption against your total bucket limit. It gives a summary metric, telling you exactly what percentage of your allotted space is used.

Can I use `list_directory` to see files inside subfolders? +

Yes, list_directory reads the contents of a specified path. You can point it at a folder like /images/assets/ to list everything within that subdirectory.

What should I use if I need to add a new asset? Should I use `create_text_file`? +

Yep, create_text_file is the tool for uploading assets. You give it the file path and the content string, and it handles writing the text data directly to your bucket.

Is there a specific way to check if a file exists using `get_file_info`? +

Running get_file_info on a specific path will confirm existence. If the file isn't found, the tool returns an error, which your agent uses to let you know it's missing.

What credentials do I need to use tools like `list_directory`? +

You need an Operator Name and Password from your UPYUN API access page. Plug these credentials into your agent, and the MCP handles the complex authorization process for you.

How does the system secure file operations when I use `create_text_file`? +

The MCP abstracts away the legacy HMAC-SHA1 Authorization header generation. You don't have to worry about generating these headers; your agent handles it securely.

If I try to delete a file that doesn’t exist using `delete_file`, what happens? +

The system reports the failure directly. The agent will tell you if the file path is invalid or if the deletion attempt failed, keeping your workflow clear.

Does `list_directory` handle large buckets efficiently? +

Yes. It lists files and folders in an UPYUN directory structure. The tool lets you check contents without needing to download manual command line clients or process massive data dumps.

Where do I find my UPYUN Operator details? +

Log into your UPYUN console, click on 'Cloud Storage' -> 'Your Service/Bucket' -> 'Configuration' -> 'Operators'. From there you can copy the operator name and the generated password.

Does the AI see my files if I connect this? +

The AI uses this MCP to only perform the standard API queries you allow it. Use an Operator with specific folder limits if you wish to restrict directory access.

Connect to your AI in seconds.

Create text file

Delete file

Get file info

UPYUN Developer Platform: 5 Tools for Cloud Operations

Make your AI actually useful.

Create Text File

Delete File

Get File Info

Get Service Usage

List Directory

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Manually managing cloud assets feels like running a dozen different CLI commands.

The UPYUN Developer Platform MCP Server: File & Bucket Operations

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

A new page needs assets uploaded and checked.

The site is running low on space.

Old development assets need to be purged.

Deploying a quick patch requires a new file.

Test

The honest tradeoffs

Assuming listing shows everything.

Trying to delete a directory.

Over-relying only on `get_file_info`.

Ignoring service limits.

When It Fits, When It Doesn't

Questions you might have