Sirv MCP. Manage CDN assets, bandwidth, and billing from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Sirv MCP Server lets your AI agent manage every file asset and billing detail in your CDN account. You can list directories, check file metadata—like size or format—monitor bandwidth usage, audit storage consumption, and delete old files.
Everything happens via natural language chat, letting you skip the dashboard entirely.
What your AI agents can do
Delete file
Permanently removes a specified file from your Sirv storage. This action is irreversible.
Get account stats
Retrieves an overview of your total account storage usage and overall traffic statistics.
Get billing info
Pulls specific financial data related to your Sirv service billing cycle.
Your AI agent lists all files and folders within a specified directory path.
The agent searches your entire asset library for files matching specific criteria or keywords.
You get technical details (format, size, dates) for a single file without downloading it.
The agent removes unused or outdated media assets from your Sirv storage. Note: this action is irreversible.
You audit current bandwidth usage, total storage consumption, and request counts for the account period.
The agent pulls specific financial details related to your Sirv service plan and usage history.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Sirv MCP Server: 9 Tools for Asset Management
These tools let your agent interact with every aspect of your Sirv CDN account—from file browsing to billing reports—using natural language commands.
019d7608delete file
Permanently removes a specified file from your Sirv storage. This action is irreversible.
019d7608get account stats
Retrieves an overview of your total account storage usage and overall traffic statistics.
019d7608get billing info
Pulls specific financial data related to your Sirv service billing cycle.
019d7608get detailed usage
Retrieves granular metrics detailing how bandwidth and storage were used over a specific period.
019d7608get file details
Fetches technical details for one file, including its format, dimensions, and modification date.
019d7608list account users
Shows a list of every user account that has access to the Sirv instance.
019d7608list custom domains
Lists all custom domain names configured and linked to your Sirv CDN.
019d7608read directory
Reads the contents of a specific directory path, listing its contained files and subfolders.
019d7608search files
Searches across your entire asset library to find files based on keywords or metadata.
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
Make Your AI Do More
Start with Sirv, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Your AI client can manage every file asset and billing detail in your Sirv CDN account. You don't have to open up a dashboard or run messy command lines—you just talk to your agent, and it does the dirty work.
When you need to handle assets, your agent starts by checking where things are. It can use list_account_users to see who has access to the Sirv instance, giving you an immediate roster of collaborators. You can check which custom domains are hooked up by running list_custom_domains, making sure every endpoint is correctly configured.
Need to know what's inside a folder? Just tell it the path, and your agent executes read_directory. It spits out everything contained in that specific directory—all the files and any subfolders nested deep inside. If you need to find something without knowing the exact location, use search_files. This tool searches across your entire asset library, letting you track down assets based on keywords or metadata tags.
Once you pinpoint a file, you can get its technical specs instantly using get_file_details. You'll get the format, dimensions, and modification date without ever having to download a single byte. For an overview of everything stored, run get_account_stats to check your total storage usage and overall traffic numbers.
Monitoring consumption is straightforward. To drill down into exactly how bandwidth and storage were used over a specific time period, use get_detailed_usage. You can also pull the big picture on resource limits by calling get_account_stats, giving you an audit of your current usage against your plan's capacity.
If it's time to clean house, your agent handles asset deletion. Running delete_file permanently removes a specified file from Sirv storage. Remember, that action is irreversible.
For billing and account audits, the system has two dedicated tools. You can pull specific financial data related to your service plan and usage cycle using get_billing_info. For broader metrics on what's happening with the entire account—like checking who needs access or listing domains—you use list_account_users and list_custom_domains, respectively.
Everything you need—from listing contents via read_directory to finding a specific image using search_files and then deleting it with delete_file—happens entirely through natural chat. It's all about direct action, giving your agent full control over file management and financial tracking in Sirv.
How Sirv MCP Works
- 1 Add the Sirv integration credentials (Client ID, Client Secret) to your AI toolset.
- 2 Your AI client uses natural language to generate specific API calls (e.g., 'Show me bandwidth usage for this month').
- 3 The server executes the call and returns structured data—like file lists or usage graphs—right back into your chat window.
The bottom line is that your agent speaks Sirv's API language, letting you manage assets through conversation instead of a web UI.
Who Is Sirv MCP For?
This is for anyone who spends time in asset management or development operations. Think of the E-commerce Manager who hates clicking through 10 dashboard tabs just to clean up product images, or the Web Developer who needs quick file metadata without breaking flow state. If you deal with CDN content and usage costs, this saves you time.
Auditing vast libraries of product photos to find unused versions or managing large-scale asset deletions before a site refresh.
Checking if the correct version of an image is live on the CDN, verifying its metadata, or listing custom domains for testing.
Monitoring storage capacity and bandwidth usage monthly, and organizing media assets by reading directory structures.
What Changes When You Connect
- Audit storage usage instantly. Instead of clicking into the Usage dashboard to see if you're nearing your limit, use
get_account_statsorget_detailed_usageto get a clear percentage and metric breakdown immediately. - Quickly audit assets for cleanup. Need to find all old product logos? Use
search_filesto target specific metadata across millions of files, bypassing the manual folder navigation entirely. - Understand your costs without logging into billing portals. Run
get_billing_infoor check usage withget_detailed_usageto see exactly what drove up last month's bill—and when it happened. - Manage content structure via chat. Use
read_directoryto list the contents of a specific folder path, letting you plan out asset changes and confirm file locations before runningdelete_file. - Inspect assets on the fly. You can run
get_file_detailsfor any file ID to check its size or format without having to download it first, perfect for web development checks. - Verify domain setup easily. Use
list_custom_domainsto confirm which custom domains are active and linked to your Sirv account at a glance.
Real-World Use Cases
Cleaning up an abandoned product line's assets
The Content Manager knows the 'Fall 2022' folder is full of unused images. Instead of logging in and manually browsing, they ask their agent to read_directory first, confirm the contents, then tell it to run delete_file on all JPEG assets older than two years. The cleanup happens in three chat commands.
Debugging a missing product image
The Front-End Developer sees an error for a specific asset ID. They ask the agent to get_file_details on that ID immediately. The agent returns the format, size, and last modified date in seconds, letting the developer confirm if the file is corrupt or just mislinked.
Budget planning for next quarter's growth
The E-commerce Director needs to know if they can handle a massive marketing push. They ask their agent to run get_account_stats and follow up with get_detailed_usage. This gives them the bandwidth ceiling, allowing them to plan purchases based on hard data.
Checking compliance after staff turnover
The Ops Engineer suspects former employees left sensitive assets lying around. They use list_account_users to confirm who had access and then run a targeted search_files query for specific keywords ('draft,' 'internal') across the entire asset pool.
The Tradeoffs
Trying to guess file structure
Typing 'list all images in my account' without specifying a path. The agent fails because it doesn't know which directory you mean, leaving you stranded.
→
Always start by using read_directory and providing the absolute path (e.g., '/marketing/campaigns'). This confirms the structure first before you try to operate on files.
Overlooking billing details
Assuming that low usage means zero cost, leading to unexpected overage charges later because they didn't check the actual data.
→
Never assume. After any major operation (like a large delete_file batch), run get_billing_info and get_detailed_usage to confirm the financial impact.
Running deletion without confirmation
Asking the agent to 'clean up old stuff' with a broad prompt, resulting in it deleting mission-critical assets because it lacked specific instructions.
→
Always scope your delete requests. First, use search_files to find exactly what needs to go, then verify the list, and finally call delete_file on that confirmed set.
When It Fits, When It Doesn't
Use this MCP Server if your primary need is managing media assets (images, videos) stored in a CDN environment, or tracking the associated bandwidth/storage usage. The core tools revolve around CRUD operations: listing (read_directory), reading metadata (get_file_details), creating visibility (search_files), and deleting (delete_file). Don't use it if you need complex business logic—like triggering an email campaign, updating a CRM record, or running payroll. For those tasks, you need integration with messaging platforms or dedicated backend APIs (e.g., a ticketing system tool). Stick to asset management and usage auditing.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sirv. 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
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 server provides 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually managing assets across dashboards is exhausting.
Right now, if you need to check the metadata on three different product photos, your workflow looks like this: Open Sirv dashboard -> Navigate to 'Images' folder -> Select photo 1 -> Click 'Details' tab. Repeat for photo 2 and photo 3. Then, you have to switch tabs just to see how much bandwidth was used that month.
With the Sirv MCP Server, your agent does it all in one chat exchange. You ask: 'What are the dimensions of asset X, and what's our total bandwidth usage?' The agent runs `get_file_details` and `get_account_stats`, giving you both answers instantly. It’s just data, delivered fast.
Using Sirv MCP Server with the delete_file tool
Before this server, removing assets meant logging in and navigating to the specific file's folder. You’d have to manually confirm deletion one file at a time, hoping you didn't miss any duplicates or old versions.
Now, your agent handles it all. You prompt: 'Delete every image in the /archive/ folder that hasn't been accessed in two years.' The agent uses `read_directory` and then runs batch commands to clean up the waste, giving you a confirmation count so you know exactly what's gone.
Common Questions About Sirv MCP
How do I use the delete_file tool with Sirv MCP Server? +
You tell your agent which file to remove and provide its unique ID or path. Always confirm the specific asset details first using get_file_details before running delete_file, since this action is permanent.
What information can I get with get_account_stats? +
This tool gives you a high-level snapshot of your entire Sirv account, showing total storage used and overall traffic statistics. It's the fastest way to check if you have capacity left.
Can I find specific assets using search_files? +
Yes. You can use search_files to look for files across your entire library by keyword, size, or metadata tags. This is way faster than browsing folder structures.
How do I check my current billing details with get_billing_info? +
Simply ask the agent to run get_billing_info. It pulls your account's financial summary, letting you see the costs and usage period without needing to log into a separate finance portal.
What path do I need for the `read_directory` tool? +
It requires an absolute path starting with "/". This ensures your agent knows exactly which folder to read. You can list the contents of any specific directory in your Sirv account.
How do I use `get_file_details` to check an asset's dimensions or format? +
The tool retrieves detailed metadata for a single file, giving you its dimensions, format (like JPEG or PNG), size, and modification dates. You just need the specific file ID.
What information does `list_custom_domains` provide about my account setup? +
This tool lists every custom domain currently configured for your Sirv account. It helps you verify that all external domains are connected and pointing to the correct assets.
How can I check my detailed usage metrics using `get_detailed_usage`? +
This tool provides a granular breakdown of resource consumption beyond simple totals. It helps you pinpoint exactly where your bandwidth or storage is being used, which is useful for auditing.
Can it accidentally delete all my files? +
The delete_file tool only removes the specific file you target by path. It cannot delete entire directories at once. Each deletion requires an explicit file path.
How does authentication work? +
You provide your Client ID and Client Secret. The integration automatically exchanges them for a Bearer token on each session — no manual OAuth setup required.
What file types does Sirv support? +
Sirv supports images (JPEG, PNG, WebP, SVG, GIF), videos, PDFs, and other static files. The integration can browse and manage all file types stored in your account.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Truto Unified Calendar
Empower your AI agent with a universal API to read, schedule, and sync events seamlessly across Google, Outlook, and other major calendar providers.
Dataiku DSS
Manage data science via Dataiku — list projects and datasets, track pipeline jobs, run automation scenarios, and monitor ML models directly from any AI agent.
OpenAI Alternative
Manage OpenAI resources via API — list models, monitor fine-tunes, manage batches and inspect Assistants from any AI agent.
You might also like
Sunrise-Sunset
Get precise sunrise, sunset, and twilight times for any location on Earth using latitude and longitude coordinates.
Cloudbeds
Manage hotel reservations, guests, rooms, housekeeping, availability, and revenue dashboard for your Cloudbeds property through natural conversation.
Agendor
CRM for sales teams — manage leads, organizations, and pipelines via AI.