
Connect Fastly to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your CDN and edge cloud through natural conversation.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 12 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 12 available through Fastly.
- 01
Create service
This capability creates a new Fastly service for your edge configuration.
- 02
Delete service
Use this to remove a specific Fastly service from your account.
- 03
Get me
This capability retrieves the identity information for your current API token.
- 04
Get service
Get detailed configuration data for a specific Fastly service.
05-08
4 capabilities in this set.
Part of 12 available through Fastly.
- 05
List version backends
This capability lists all backend origins associated with a specific service version.
- 06
List version domains
Get a list of all domains configured for a specific service version.
- 07
List services
This capability returns a list of all Fastly services in your account.
- 08
List service versions
Retrieve all configuration versions available for a given service.
09-12
4 capabilities in this set.
Part of 12 available through Fastly.
- 09
Activate service version
Use this to promote a specific configuration version to active status.
- 10
Get service stats
This capability pulls usage statistics for a specific Fastly service.
- 11
Get service version
Get the specific details of a single service version.
- 12
Purge all cache
This capability issues a command to purge all cached content for a service.
Real work
What teams actually run
Emergency Cache Clearing
When a bad asset is deployed, you tell your agent to purge the cache for a specific service immediately.
Rapid Security Patching
Deploy a new security configuration by asking your agent to promote a drafted version to active.
Backend Auditing
Verify that your Fastly configurations are correctly pointing to your AWS or GCP origins.
Routing Verification
Check FQDN apex domains and routing configurations without logging into the Fastly portal.
Automate a task
Put Fastly to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Fastly works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Fastly to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
974ms average. Fast in production.
Fastly is checked daily against the live service.
- Fastest day
- 834ms
- Slowest day
- 1231ms
- 14-day trend
- Slowing+45%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Fastly, so you can see the experience inside your AI.
It does not authenticate your account with Fastly. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Fastly Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_DoQHJFChafBsNpZF2vkvStONLhFdmK4tw0VbuS3U/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Fastly capabilities are ready to use.
{
"mcpServers": {
"fastly-mcp": {
"url": "https://edge.vinkius.com/vk_preview_DoQHJFChafBsNpZF2vkvStONLhFdmK4tw0VbuS3U/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Fastly in Claude and other AIs
Who it's for
Built for the work Fastly owners hand off.
This MCP is built for technical teams managing high-traffic edge networks who want to move faster than the dashboard allows.
- 01
DevOps & SRE Teams
They use the agent to monitor service versions and trigger rapid cache purges.
- 02
Cloud Architects
They audit backend origin mappings and domain configurations via chat.
- 03
Security Engineers
They deploy instant security patches by activating drafted versions.
- 04
Frontend Developers
They verify CDN configurations and test edge routing logic from their IDE.
FAQ
Questions Fastly owners ask.
- 01
How do I connect this MCP to my AI client?
You subscribe to the Fastly MCP on Vinkius and provide your Fastly API Token. Once connected, you can use it immediately in any MCP-compatible client like Claude or Cursor.
- 02
What credentials do I need?
You need a Fastly API Token, which you can generate in your Fastly Control Panel under Account and then API tokens.
- 03
Can I purge my cache using this capability?
Yes, you can issue a command to purge all cached content for a specific service through your AI agent.
- 04
Is it safe to deploy versions through an AI agent?
The MCP uses your existing Fastly API permissions. It executes the same 'activate service version' actions you would perform in the dashboard.
- 05
Which clients are compatible with this MCP?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 06
Can my agent purge the entire Fastly cache for a specific service?
Yes. Use the 'purge_all_cache' capability with your Service ID. The agent will issue absolute HTTP PURGE instructions globally, vaporizing the complete surrogate cache for static endpoints immediately.
- 07
How do I activate a drafted configuration version via chat?
Use the 'activate_service_version' capability. Provide the Service ID and the version number. The agent will force the compilation of that VCL version and promote the draft to active, promoting your changes to production flawlessly.
- 08
Can I check which backend origins are connected to a service version through the agent?
Absolutely. Use the 'list_version_backends' capability. Your agent will read the exact upstream AWS/GCP endpoints mapped inside your active or drafted configuration, helping you verify origin and port constraints.
Explore
More in Industry Titans
StackPath (Edge Computing & CDN API) AI Connector
Manage edge computing workloads and CDN delivery via StackPath — list stacks, deploy workloads, and purge cach
ViewKeyCDN (Content Delivery Network) AI Connector
Manage edge caching via KeyCDN — purge zones and URLs, manage pull zones, and monitor traffic bandwidth.
ViewBunny.net AI Connector
Manage Bunny.net edge infrastructure — control your CDN Pull Zones, purge caching rules, and map Storage nativ
ViewLimelight Networks (Edgio CDN & Streaming API) AI Connector
Manage Edgio (formerly Limelight/Uplynk) streaming services — control VOD assets, linear channels, and live ev
View
Suggestions
Beagle Security AI Connector
Automate security testing via Beagle Security — list projects, start tests, and retrieve results directly from
ViewKV Cache Memory Optimizer AI Connector
Deterministic calculator for LLM KV cache memory, throughput, and optimization analysis.
ViewCloudflare AI Connector
Manage DNS, Workers, KV, Pages and firewall via Cloudflare — audit records, deploy config and inspect CDN anal
ViewCilium (eBPF Networking) AI Connector
Manage Cilium eBPF networking — inspect cluster nodes, monitor daemon health, and manage networking endpoints
View
Connect Fastly to Claude, Cursor, ChatGPT & more
