Skip to main content
Glama
enesjakozh
jackwrichards

FastlyMCP

by jackwrichards
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Hybrid

FastlyMCP

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

image

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."

Related MCP server: @fastly/mcp

Getting Started

Prerequisites

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

License

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

Available Tools

2 tools
fastly_apiA

Make requests to the Fastly API. Allows accessing all endpoints of the Fastly API with custom paths, methods and parameters.

IMPORTANT USAGE NOTES FOR LLMs:

  1. When making multiple API calls, summarize the results between calls. The user doesn't see raw API responses.

  2. Base URL is automatically added - just provide the path (e.g. '/service').

  3. Authentication is handled automatically - no need to include API keys or know API keys.

  4. Common paths:

    • List services: GET /service

    • Get service details: GET /service/{service_id}

    • Get domains: GET /service/{service_id}/version/{version}/domain

    • Get backends: GET /service/{service_id}/version/{version}/backend

    • Purge cache: POST /service/{service_id}/purge_all

    • Get stats: GET /stats (with params: service_id, from, to)

  5. Always check status codes in responses. Status 200-299 indicates success.

  6. Include simple explanations of what you're doing and what the results mean before and after each API call.

Creating Fastly Compute@Edge Sites

To create a Compute@Edge site, you can use a combination of API calls and terminal commands. The API handles service creation and configuration, while terminal commands handle the local build and deployment process.

Follow these general steps:

  1. Create a new service using the API: POST /service with {"name": "My Site", "type": "wasm"}

  2. Initialize a local Compute project using the Fastly CLI

  3. Build the project using the appropriate build tools

  4. Deploy using the Fastly CLI with the service ID from step 1

COMMON PITFALLS TO AVOID:

  1. DO NOT use --name flag with fastly compute init (use interactive mode or -d -y flags instead)

  2. PowerShell requires semicolons (;) not ampersands (&&) for command chaining

  3. Fastly compute build creates the package archive AFTER you've built the Wasm binary

  4. Build is a TWO-STEP process: first compile to Wasm, then create the package archive

  5. Deploy command needs -d flag to avoid hanging on interactive prompts

  6. NEVER attempt to extract or use the user's API key directly - auth is handled by MCP

  7. To create a service from scratch, you must use API calls for configuration and CLI for local build

  8. Check current directory paths carefully before running commands

  9. Full URL paths aren't needed in API calls - just use the path portion (e.g. '/service')

See the full guide for detailed instructions on handling common errors and PowerShell-specific commands.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesAPI path (e.g., '/service' or '/service/{service_id}/purge_all'). Don't include base URL.
methodYesHTTP method (GET, POST, PUT, DELETE)
bodyNoRequest body for POST/PUT requests (optional). Will be JSON-encoded automatically.
paramsNoURL parameters to add to the request (optional). For filtering, pagination, etc.

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure and excels at this. It explains authentication handling ('Authentication is handled automatically'), response handling ('summarize the results between calls'), status code interpretation ('Always check status codes'), and important constraints ('Base URL is automatically added', 'Full URL paths aren't needed'). It also provides detailed guidance about what the LLM should do before/after calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is excessively long (over 500 words) with multiple sections that could be streamlined. While the front-loaded 'IMPORTANT USAGE NOTES' is well-structured, the later sections on 'Creating Fastly Compute@Edge Sites' and 'COMMON PITFALLS' contain information that belongs in documentation rather than a tool description. Many sentences don't directly help the agent select/invoke the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a generic API tool with 4 parameters and no output schema, the description provides substantial context about usage patterns, common endpoints, authentication, and response handling. It covers most aspects needed for effective use, though it could benefit from more detail about error responses or rate limits. The absence of an output schema is partially compensated by guidance on interpreting status codes and summarizing results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds significant value beyond the schema by providing concrete examples of paths ('/service', '/service/{service_id}/purge_all'), explaining how parameters work ('with params: service_id, from, to'), and clarifying that the body is 'JSON-encoded automatically'. However, it doesn't fully explain all parameter nuances like how 'params' object maps to URL parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Make requests to the Fastly API' with access to 'all endpoints', which is specific about the verb (make requests) and resource (Fastly API). It distinguishes from the sibling tool 'fastly_cli' by focusing on API calls rather than CLI commands. However, it doesn't explicitly contrast with the sibling tool beyond mentioning CLI in the usage notes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides extensive usage guidance including explicit when-to-use scenarios (e.g., 'When making multiple API calls', 'To create a service from scratch'), alternatives (CLI for local build/deployment), and exclusions (e.g., 'NEVER attempt to extract or use the user's API key directly'). The 'IMPORTANT USAGE NOTES' section offers comprehensive context for when and how to use this tool versus other approaches.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fastly_cliA

Execute Fastly CLI commands securely without exposing API keys.

This tool allows you to run Fastly CLI commands while the MCP server handles authentication automatically. The LLM never sees or needs to handle the API key directly.

USAGE EXAMPLES:

  1. Initialize a Compute project: fastly_cli('compute init --language javascript -d -y')

  2. Build a package: fastly_cli('compute build')

  3. Deploy a service: fastly_cli('compute deploy --service-id SERVICE_ID -d -y')

COMMON COMMANDS:

  • compute init: Initialize a new Compute project

  • compute build: Build a Compute package

  • compute deploy: Deploy a Compute package

  • compute publish: Build and deploy in one step

  • whoami: Check authentication status

SECURITY NOTE: Authentication is handled automatically. Never attempt to pass API keys in commands.

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesThe Fastly CLI command to execute (without the 'fastly' prefix)
working_directoryNoOptional working directory for command execution

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it's a command execution tool with automatic authentication handled server-side, security warnings against passing API keys, and examples of common commands. It doesn't cover all potential behaviors like error handling or output format, but provides substantial context beyond basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (purpose, usage examples, common commands, security note) and front-loads the core purpose. It's appropriately sized for a CLI tool, though the 'COMMON COMMANDS' section could be slightly more concise as it lists commands already implied by examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (CLI command execution with security considerations), no annotations, and no output schema, the description does a good job of providing necessary context. It covers purpose, usage, examples, security, and common commands. However, it doesn't describe what the tool returns (output format/behavior), which is a gap since there's no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, clearly documenting both parameters. The description adds minimal parameter semantics beyond the schema—it implies the 'command' parameter should exclude the 'fastly' prefix through examples, but doesn't explicitly state this. With high schema coverage, the baseline score of 3 is appropriate as the schema does most of the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Execute Fastly CLI commands securely without exposing API keys.' It specifies the exact action (execute CLI commands) and resource (Fastly CLI), and distinguishes it from the sibling 'fastly_api' tool by focusing on CLI execution rather than API calls.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool (running Fastly CLI commands with automatic authentication) and includes usage examples and common commands. However, it does not explicitly state when NOT to use it or directly compare it to the 'fastly_api' sibling tool, which would be needed for a perfect score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updates
    • First observedfastly_api
    • First observedfastly_cli
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

The two tools have completely distinct purposes: fastly_api handles direct API calls for service management, configuration, and data retrieval, while fastly_cli executes CLI commands for local project development and deployment. There is no overlap in functionality, making it clear when to use each tool.

Naming Consistency5/5

Both tools follow a consistent naming pattern with the prefix 'fastly_' followed by a descriptive suffix (_api, _cli). This clear and uniform naming scheme makes it easy to identify the tool's purpose at a glance.

Tool Count3/5

With only 2 tools, the server feels thin for covering Fastly's comprehensive CDN and edge computing platform. While the tools cover API interactions and CLI operations, many domain-specific actions (e.g., cache management, analytics, configuration updates) are deferred to generic API calls, which may require more agent effort to construct properly.

Completeness2/5

The tool set is severely incomplete for the Fastly domain. While fastly_api provides generic API access, there are no dedicated tools for common operations like purging cache, managing domains/backends, or retrieving statistics—forcing agents to manually construct API paths. The CLI tool helps with Compute@Edge but doesn't cover other Fastly services, leaving significant gaps in coverage.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Fastly NGWAF MCP Server

    purpleax
    A
    license
    B
    quality
    D
    maintenance
    Provides seamless integration with Fastly's Next-Gen Web Application Firewall API, enabling AI assistants to manage web application security through natural language interactions.
    29
    1
    MIT
  • @fastly/mcp by fastly

    @fastly/mcpofficial

    fastly
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables assistants to interact with the Fastly API, allowing them to manage services, domains, TLS settings, traffic, dictionaries, ACLs, purge content, and make configuration changes.
    108
    39
    MIT

  • nextdns-mcp

    dmeiser
    A
    license
    A
    quality
    A
    maintenance
    Enables AI assistants to manage NextDNS profiles, settings, logs, analytics, and security configurations through 70+ operations via the Model Context Protocol.
    8
    10
    MIT
  • Files.com MCP Server by Files-com

    Files.com MCP Serverofficial

    Files-com
    A
    license
    C
    quality
    B
    maintenance
    Enables AI models to perform file operations, user management, automations, and more within Files.com's secure file transfer platform via the Model Context Protocol.
    65
    2
    MIT

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jackwrichards/FastlyMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server