FastlyMCP

Fastly MCP brings the power of Fastly's API directly to your AI assistants through the Model Context Protocol (MCP).

Fastly's API-First Approach

Fastly's API-first design philosophy means:

• Everything is an API - Every feature available in the Fastly UI is accessible via API
• Programmatic Control - Full control over services, configurations, and edge logic
• Automation Ready - Support for CI/CD workflows and infrastructure as code
• Real-time Changes - API changes propagate globally in seconds, not minutes or hours

What Can I Do With Fastly API?

Fastly's comprehensive API allows you to:

• Manage CDN Services - Create, configure, and deploy content delivery services
• Control Caching - Set up cache strategies and perform instant purges
• Configure Security - Manage WAF, DDoS protection, and TLS certificates
• Monitor Performance - Access real-time metrics and historical stats
• Implement Edge Logic - Deploy custom VCL or Compute@Edge applications
• Automate Workflows - Integrate with CI/CD pipelines and infrastructure tools

Your API Key Stays Safe!

The AI assistant never sees your Fastly API key. It talks to a local helper (FastlyMCP) which uses the key securely.

What You Can Ask Your AI

With Fastly MCP configured, you can ask your AI assistant questions like:

What You Want To Do	Example AI Request
List your services	"Show me all my Fastly services"
Get domain details	"What domains are configured for my e-commerce service?"
Purge cache	"Purge the cache for my product service"
Check traffic	"What's the traffic pattern for my main site over the last week?"
View configuration	"Show me the backend servers for my API service"
Check performance	"What's my current cache hit ratio?"

"What the traffic pattern my for services over the last week?"

"List all my Fastly services and their domains."

"Build an interactive preformance dashboard about my Fastly serivce."

Getting Started

Prerequisites

• A Fastly account and API key (Get started with Fastly)
• An AI assistant that supports MCP (e.g., Claude, GPT with plugins)
• The Fastly CLI installed (Installation Guide)

Connect Your AI Assistant

Configure your AI assistant with:

{
  "mcpServers": {
    "fastly": {
      "command": "node",
      "args": ["path/to/fastly-mcp.mjs"],
      "env": {
        "FASTLY_API_KEY": "your_fastly_api_key"
      }
    }
  }
}

Advanced Operation Examples

Task Goal	Example AI Request
Optimize service based on traffic	"Analyze the configuration for [service_id/name] and suggest optimizations based on its traffic profile, prioritizing low latency."
Configure for live video	"Configure [service_id/name] for optimal live video streaming following the best practices outlined in [link_to_guide_or_doc]."
Find config conflicts	"Identify potential configuration conflicts in [service_id/name] compared to standard e-commerce delivery patterns."
Optimize video chunk caching	"Optimize caching for [service_id/name] to handle 10-second video chunks efficiently, minimizing origin load."
Enhance WAF security	"Review the WAF rules for [service_id/name] and suggest stricter settings to mitigate potential SQL injection attacks."
Set up origin mTLS	"Set up Mutual TLS (mTLS) authentication between Fastly and the origin servers for [service_id/name]."
Implement A/B testing (Edge)	"Deploy a Compute@Edge function to [service_id/name] that performs A/B testing by routing 10% of users to backend [backend_name]."
Add dynamic image rewriting (VCL)	"Write and deploy VCL for [service_id/name] to dynamically rewrite image URLs based on the requesting device's user agent."
Troubleshoot 5xx errors	"Analyze logs for [service_id/name] from the past 24 hours to identify the root cause of the recent spike in 5xx errors."

Learn More

• Fastly API Documentation
• Model Context Protocol
• Getting Started with Fastly

License

This project is licensed under the MIT License - see the LICENSE file for details.