StackPath MCP for AI. Control global CDNs and edge workloads from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
StackPath manages global edge computing deployments and CDN delivery via a single API gateway. You can list all resource stacks, deploy containerized workloads to specific regions, create new content delivery sites, or instantly purge cached content across your entire network using natural conversation with any AI agent.
What AI agents can do with StackPath (Edge Computing & CDN API) Automation
Create cdn site
Sets up a brand new content delivery network site pointing to your origin.
Create workload
Deploys and provisions compute capacity (a workload) at an edge location.
List cdn sites
Retrieves a list of all CDN sites currently configured within a stack.
List all high-level resource containers (stacks) across your global edge network.
Create and deploy containerized or virtual machine workloads to specific edge locations for low latency.
Set up new content delivery network (CDN) sites pointing to your origin servers.
Instantly clear cached content from the CDN, ensuring users see live updates across all nodes.
Retrieve current lists of deployed stacks, CDNs, and workloads for quick status checks.
Ask an AI about this
Waiting for input…
What AI agents can do with StackPath (Edge Computing & CDN API) MCP Server: 6 Tools for Cloud Ops
Use these tools to manage your entire edge infrastructure—from listing high-level stacks to deploying workloads and purging cached content.
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 StackPath (Edge Computing & CDN API) on VinkiusCreate Cdn Site
Sets up a brand new content delivery network site pointing to your origin.
Create Workload
Deploys and provisions compute capacity (a workload) at an edge location.
List Cdn Sites
Retrieves a list of all CDN sites currently configured within a stack.
List Stacks
Fetches the names and IDs of every logical container (stack) in your account.
List Workloads
Lists all active compute workloads running inside a specific stack.
Purge Content
Triggers an immediate purge request, clearing cached content across the entire CDN network.
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 StackPath integration is available immediately — no restart needed.
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 StackPath (Edge Computing & CDN API), 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by StackPath. 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
Built on the Model Context Protocol (MCP) for 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 6 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Dealing with Global Cache Issues Isn't Just 'A Problem', It's an Emergency., Solved with Vinkius AI Gateway
Today, if your product has a bug fix or a major asset update, you have to wait for the cache to expire. You log into the CDN portal, hit 'Purge,' and then you just sit there, staring at a progress bar that moves too slowly. Meanwhile, users across Europe see the old logo, and users in Asia see the broken feature.
With this MCP Server, you don't wait. You tell your agent: 'Purge the cache for my latest banner image.' It submits the request to StackPath and confirms it instantly. You get immediate confirmation that the content is being invalidated everywhere.
StackPath (Edge Computing & CDN API) MCP Server: Control Your Entire Edge.
Before this, deploying a new service meant juggling separate portals: one for creating the stack, another for pointing the CDN name, and yet a third place to deploy the actual containerized code. It was slow, complex, and required deep knowledge of five different CLI flags.
Now, you talk to your agent about what you want done—'Set up a new staging environment with this workload.' The agent handles the sequence: it checks if the stack exists, creates it if needed (`list_stacks` / `create_workload`), and ensures the CDN is pointing correctly. It’s all one conversation.
What your AI can actually do with this
This server lets you manage your entire edge infrastructure and content delivery network (CDN) straight from any AI agent. You don't gotta log into some clunky console; you just talk to your client, and it handles the heavy lifting of deploying resources across a global footprint.
Manage Infrastructure Stacks. You need a high-level view of where everything lives? Use list_stacks to pull up the names and IDs for every single logical container—every stack—you've deployed across your network. This gives you one place to see all your resource groupings, keeping your massive infrastructure organized.
List Active Resources. Need a quick status check on what’s running right now? If you want to know what CDNs are up and humming, list_cdn_sites pulls that list for you. Similarly, if you wanna check the compute workloads inside a specific stack, list_workloads gives you a rundown of all active containers or VMs currently operating there.
Configure CDN Sites. Gotta roll out new content delivery? You use create_cdn_site. This tool sets up a brand-new CDN endpoint that points directly to your origin servers. It's how you make sure fresh content hits the edge network exactly where it needs to go.
Force Cache Purges. Users shouldn't see old stuff, right? When you run purge_content, you trigger an immediate purge request that clears out cached content across the entire CDN network. It’s instant; every node gets hit so your users only see the live updates.
Deploy Edge Workloads. You need low latency and compute power at a specific corner of the globe? Use create_workload. This tool deploys and provisions full compute capacity—whether it's containerized or a virtual machine workload—at an exact edge location. This means your app runs fast, no matter where your user is.
When you combine these functions, you're controlling the whole lifecycle of your global edge presence. You can list every stack using list_stacks, then use that stack ID to deploy compute capacity via create_workload. Once that workload is live, if you need a new delivery endpoint for it, you run create_cdn_site.
If you need to verify the CDN site exists, check with list_cdn_sites. You can't forget about keeping things current; after any major deployment or content change, running purge_content ensures stale data never makes it to a user. Finally, if you just wanna confirm everything is deployed and working before calling anyone, you use list_workloads to verify the compute status.
019e5d59-518b-73a0-9477-6982d2b57302 
Here's how it actually works
The bottom line is you manage complex global infrastructure by simply talking to your AI agent instead of writing specific CLI commands.
Subscribe to this server and provide your StackPath Client ID and Secret.
Your AI client authenticates with the Vinkius Marketplace using these credentials.
You ask your agent to perform an action (e.g., 'Purge the cache for example.com'). The agent calls the appropriate tool, executes the command, and reports the result.
Who is this actually for?
The SRE team that gets paid for waking up at 3 AM. You're the full-stack developer who hates context switching between the IDE and a dozen different cloud portals. This is for anyone whose job requires managing global, distributed systems where caching issues are a daily threat.
Automates routine maintenance tasks like running purge_content or deploying new stacks (list_stacks) without leaving their terminal workflow.
Quickly inspects infrastructure health by listing workloads (list_workloads) and checking CDN status across multiple regions during an incident response.
Checks the current operational state of edge containers or CDNs using list_cdn_sites without breaking focus from coding the front end.
What Changes When You Connect
Force cache purges with purge_content. When you push an update, the content is instantly invalidated everywhere. No more stale images or old data showing up for users—it just works.
Manage resources at scale by running list_stacks. See all your separate development, staging, and production environments in one call, so you know exactly which stack you're touching.
Deploy compute power with create_workload. You can spin up a new containerized service right at the edge for super low latency without manual SSH into multiple regions.
Get an instant infrastructure status check using list_cdn_sites or list_workloads. This is way faster than opening ten different tabs and running commands one by one.
Create new endpoints with create_cdn_site. When you launch a new product line, you don't have to manually configure the CDN—you just call the tool.
See it in action
The emergency hotfix rollout
A developer pushes an urgent fix that needs instant global visibility. Instead of waiting 2 hours for cache expiration, they ask their agent to run purge_content on the production stack. The system confirms the purge request is submitted immediately, guaranteeing users see the new code right away.
Scaling a new feature area
A team needs a dedicated environment for testing a high-traffic regional service. They run list_stacks to confirm available names, and then use create_workload to spin up the compute capacity in the required region without touching production.
Auditing old deployments
An SRE needs to check if a deprecated service is still running anywhere. They run list_stacks, find the relevant stack ID, and then immediately call list_workloads to see exactly what compute resources are consuming capacity.
Launching a new marketing site
Marketing needs a temporary landing page for a campaign. They use their agent to run create_cdn_site, point it at the correct origin, and get a live endpoint URL back—all in seconds.
The honest tradeoffs
Treating infrastructure as code
Trying to manually track which stack holds which workload ID by reading dozens of YAML files. This is slow, error-prone, and only tells you what should be running.
Don't read config files. Use list_stacks first to identify the target container, then use list_workloads to get an accurate, real-time inventory of deployed resources.
Assuming cache clears automatically
A developer pushes a critical CSS fix and assumes it'll propagate in 30 minutes. The site looks broken across half the globe because the CDN is still serving old content.
Never assume propagation time. Always call purge_content after any major asset change to force immediate global cache invalidation.
Over-relying on a single API endpoint
If you only use one tool, like list_cdn_sites, you might forget that the site isn't running if there are no workloads deployed. You miss half the picture.
Always check both sides: run list_cdn_sites for content delivery status, and then run list_workloads to confirm the compute engine is actually online.
When It Fits, When It Doesn't
Use this MCP Server if your application relies on a globally distributed edge network (CDN + Compute) and you need to manage resources across multiple logical environments (stacks).
Don't use it if: 1. You only run one small web server in a single region, or 2. You are building an internal API that never needs public content delivery.
If you just need to check simple resource lists without taking any action, basic cloud CLI tools might suffice. But if your job involves deployment (create_workload), making the site live (create_cdn_site), or fixing a cache problem (purge_content) across multiple environments simultaneously—this is essential.
Questions you might have
How do I check all my environments using list_stacks? +
Run list_stacks. This tool returns a complete inventory of every logical container you have set up, giving you the exact stack IDs needed for subsequent operations.
What's the difference between list_cdn_sites and list_workloads? +
list_cdn_sites shows your public-facing URLs and how they are routed. list_workloads tells you if the actual compute engine (the code running) is active inside a stack.
If I run purge_content, does it clear everything? +
Yes, purge_content forces an immediate cache flush across the entire configured CDN network for your specified content. It's the fastest way to ensure freshness.
Can I deploy a new service without knowing the stack ID? +
No, you usually need the context of existing stacks first. Use list_stacks to get all available IDs, and then reference that ID when calling create_workload.
When I run `create_cdn_site`, what specific formats must the hostname and origin URL follow? +
Both require standard, fully qualified domain names (FQDNs). The hostname is your public-facing site address. The origin must be an accessible internal endpoint that hosts the raw content you want served.
If `create_workload` returns an error, what status code tells me it's a resource limit issue? +
The tool response will include an explicit error object detailing the failure. Look for HTTP 429 or specific messages indicating that the target stack has exceeded its allocated container count.
After running `purge_content`, how long until the cached content is gone globally? +
The purge request submits immediately, but cache invalidation propagates across edge nodes. You should expect full global clearance within a few minutes, depending on your current network configuration.
Does `list_workloads` support querying for workloads from multiple stack IDs in one command? +
No. The tool requires you to specify a single stack ID per request. You must run the command for each stack individually and then compile the full list yourself.
How do I clear the CDN cache for specific assets? +
You can use the purge_content tool. Provide the stack_id and a list of urls you want to invalidate. You can also set recursive to true to purge entire directories.
Can I deploy a new container to the edge using this agent? +
Yes! Use the create_workload tool. You'll need to specify the stack_id, a name, slug, and the container image (e.g., 'nginx:latest').
How do I find the ID of my infrastructure stacks? +
Simply run the list_stacks tool. It will return all logical stacks associated with your account along with their unique IDs.
We've already built the connector for StackPath. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.