ALECS - MCP server for Akamai
ALECS MCP Server for Akamai is an AI-powered automation tool that provides natural language interaction and programmatic control over Akamai CDN services. With this server, you can:
Property Management: List, create, activate, and modify CDN properties and configuration rules
DNS Management: Manage zones, create/modify records, and activate DNS changes
Certificate Management: Create and manage domain validation certificates and monitor enrollment status
Content Control: Purge cache by URL or CP code, and manage network lists for access control
Multi-Customer Support: Securely manage multiple Akamai accounts via EdgeGrid authentication
AI Integration: Connect with various AI tools (Claude Desktop, Cursor IDE, VS Code) via Model Context Protocol
Comprehensive Coverage: Access all major Akamai services including Property Manager, Edge DNS, CPS Certificates, Fast Purge, Network Lists, App Security, and Reporting
Enables interaction with Akamai's CDN and edge services, including property management, Edge DNS management, SSL/TLS certificate handling, content invalidation (FastPurge), CP code management, and multi-customer account support.
Offers production-ready containers with compose configurations for simplified deployment and operation.
Built on Node.js 18+ with a modular architecture allowing deployment of focused servers for specific use cases or a monolithic server with all features.
Plans to add future capability to generate Terraform configurations from existing Akamai properties.
The codebase is fully migrated to TypeScript with strict mode enabled, providing enhanced type safety and developer experience.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ALECS - MCP server for Akamailist my Akamai properties"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
š ALECS MCP Server for Akamai
A Launchgrid for Edge & Cloud Services
AI-powered Akamai CDN management through natural language
š§ 156 Tools ⢠š 15 Services ⢠š Full EdgeRC Support ⢠┠Production Ready
šÆ What is ALECS?
ALECS bridges the gap between AI tools and Akamai's Connected Cloud Platform. Ask Claude, Cursor, or any MCP-compatible tool to manage your Akamai infrastructure using natural language and minimize context switching when creating Infrastructure-as-Code!
"List my Akamai properties" ā Complete property inventory
"Create a DNS zone for example.com" ā Zone created and configured
"Purge cache for /images/*" ā Cache invalidated instantly
"Check SSL certificate status" ā Validation progress shownRelated MCP server: Rini MCP Server
š One-Click Installation
macOS:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-claude-desktop.sh | bashWindows:
# Download and run installation script
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-claude-desktop.sh" -OutFile "install-claude-desktop.sh"
bash install-claude-desktop.shLinux:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-claude-desktop.sh | bashOne-click button:
Auto-install script:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-cursor.sh | bashOne-click button:
Auto-install script:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-lmstudio.sh | bashExtension + Server:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-vscode.sh | bashManual Setup:
Install MCP extension
Cmd/Ctrl + Shift + P"MCP: Add Server"
Command:
alecs
Auto-configure:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-windsurf.sh | bashManual Setup:
Open Windsurf Settings
Navigate to MCP Servers
Add server with command:
alecs
Simple command:
claude mcp add alecs-akamai alecsVerify:
claude mcp listš¦ Quick Start
1. Install ALECS
Choose your preferred method:
Global install:
npm install -g alecs-mcp-server-akamaiVerify:
alecs --versionmacOS/Linux:
curl -sSL https://raw.githubusercontent.com/acedergren/alecs-mcp-server-akamai/main/scripts/install-homebrew.sh | bashManual:
brew install node
npm install -g alecs-mcp-server-akamaiQuick start:
docker run -it --env-file .env ghcr.io/acedergren/alecs-mcp-server-akamai:latestSee full Docker section below for more options
2. Configure Akamai
Create ~/.edgerc with your credentials:
[default]
client_secret = your_client_secret
host = your_host.luna.akamaiapis.net
access_token = your_access_token
client_token = your_client_token3. Choose Your AI Tool
Pick your favorite AI assistant and use the one-click installers above! š
š Features
š ļø Service Coverage
Service | Tools | Key Features |
š¢ Property Manager | 25 | CDN configs, rules, activations |
š”ļø Security | 47 | Network lists, WAF policies |
š Edge DNS | 12 | DNS zones, records, DNSSEC |
š Includes | 10 | Include configurations |
š Edge Hostnames | 10 | Hostname management |
š Reporting | 9 | Analytics and metrics |
š Certificates | 8 | SSL/TLS lifecycle management |
ā” Fast Purge | 8 | Cache invalidation |
š§ Workflow | 7 | Orchestration and automation |
š Hostname Mgmt | 5 | Advanced hostname operations |
š¦ Bulk Operations | 5 | Batch processing |
šØ SIEM | 4 | Security monitoring |
šļø Rule Tree | 4 | Rule processing |
š CPCode | 2 | Traffic analysis codes |
šØ Natural Language Examples
š£ļø What You Say
"List my properties"
"Create DNS zone for example.com"
"Purge cache for /images/*"
"Check my SSL certificates"
"Show traffic for last 7 days"
"Add IP 192.168.1.0/24 to blocklist"š¤ What ALECS Does
ā
property_list ā Full inventory
ā
dns_zone_create ā Zone configured
ā
fastpurge_url ā Cache cleared
ā
certificate_status ā SSL validated
ā
traffic_report ā Analytics shown
ā
network_list_add ā IP blockedšļø Architecture
graph LR
A[š¤ AI Assistant] --> B[š ALECS Server]
B --> C[š Akamai APIs]
subgraph "š§ ALECS Components"
B1[š” MCP Protocol]
B2[š EdgeGrid Auth]
B3[š Tool Registry]
B4[šŖ Service Modules]
end
subgraph "š Akamai Services"
C1[š¢ Property Manager]
C2[š Edge DNS]
C3[š Certificates]
C4[š”ļø Security]
C5[ā” Fast Purge]
end
B --> B1
B1 --> B2
B2 --> B3
B3 --> B4
B4 --> C1
B4 --> C2
B4 --> C3
B4 --> C4
B4 --> C5š³ Docker & Deployment
Quick Start
# Standard I/O for Claude Desktop (default)
docker run -it --env-file .env ghcr.io/acedergren/alecs-mcp-server-akamai:latest
# Streamable HTTP for web/CDN deployment
docker run -it -p 8080:8080 -e MCP_TRANSPORT=streamable-http --env-file .env ghcr.io/acedergren/alecs-mcp-server-akamai:latestTransport Options
# Available transports
MCP_TRANSPORT=stdio # Default - Claude Desktop, Cursor, CLI tools
MCP_TRANSPORT=streamable-http # Web clients, CDN deployment (recommended)
MCP_TRANSPORT=websocket # Real-time bidirectional communication
MCP_TRANSPORT=sse # Legacy Server-Sent Events (deprecated)
# Transport-specific configuration
HTTP_PORT=8080 # Port for streamable HTTP (default: 8080)
HTTP_HOST=0.0.0.0 # Host for streamable HTTP
HTTP_PATH=/mcp # Base path for HTTP endpoints
CORS_ENABLED=true # Enable CORS for browser clientsAvailable Docker Images
docker pull ghcr.io/acedergren/alecs-mcp-server-akamai:latest # Full server
docker pull ghcr.io/acedergren/alecs-mcp-server-akamai:modular # Microservices
docker pull ghcr.io/acedergren/alecs-mcp-server-akamai:websocket # WebSocket
docker pull ghcr.io/acedergren/alecs-mcp-server-akamai:http # Streamable HTTPš OpenAPI-Driven Development
ALECS now features automatic tool generation from OpenAPI specifications:
# Generate new domain from API spec
alecs generate-from-api --spec ./openapi.json --domain mydomain
# Update existing tools when APIs change
alecs generate-from-api --spec ./api-v2.json --domain property --update
# Migrate legacy tools to OpenAPI patterns
alecs generate-from-api --spec ./api.json --tool ./dns-tools.ts --migrateBenefits:
š 10x faster tool development
š§ Always up-to-date with latest API changes
š Type-safe with automatic Zod schema generation
š Smart updates preserve custom logic
šÆ Zero manual work for standard CRUD operations
š Documentation
š Guide | š Description |
Complete developer guide | |
New team member onboarding | |
All 156 tools documented | |
Setup tutorials | |
Comprehensive architecture guide | |
Quick architecture lookup | |
Architecture diagrams | |
Technical system design | |
Coding standards & patterns | |
Comprehensive testing approach | |
Production deployment | |
Production operations & troubleshooting | |
Build custom tools & use OpenAPI |
š¤ Contributing
We welcome contributions! Check out our Contributing Guide to get started.
š Found a bug? Report it š” Have an idea? Suggest it ā Need help? Ask us
š License
GNU Affero General Public License v3.0 (AGPL-3.0) - see LICENSE
š Star us on GitHub ⢠š¦ Follow on NPM ⢠š³ Use with Docker
Built with ā¤ļø for Akamai by Alexander Cedergren, alex@solutionsedge.io
Available Tools
1 toolproperty.listC
List Akamai CDN properties
| Name | Required | Description | Default |
|---|---|---|---|
| contractId | No | Contract ID (optional) | |
| customer | No | Customer identifier from .edgerc | |
| groupId | No | Group ID (optional) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. 'List' implies a read operation, but the description doesn't mention authentication requirements, rate limits, pagination behavior, error conditions, or what format the properties are returned in. For a tool with zero annotation coverage, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core functionality without any wasted words. It's appropriately sized for a simple list operation and gets straight to the point. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a read operation with three parameters, the description is incomplete. It doesn't explain what 'properties' are in this context, what data they contain, whether results are paginated, or what authentication is required. For a tool that likely returns structured data, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters. The description doesn't add any parameter semantics beyond what's in the schema - it doesn't explain how parameters interact, which combinations are valid, or provide examples. Baseline 3 is appropriate when schema does the documentation work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('List') and resource ('Akamai CDN properties'), making the tool's purpose immediately understandable. It doesn't distinguish from siblings since none exist, but it's specific enough to know this retrieves CDN property listings. A 5 would require sibling differentiation which isn't applicable here.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It simply states what the tool does without indicating appropriate usage scenarios. With no siblings, the bar is lower, but still lacks any usage context.
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.
1 tool update
v1.0.0- First observed
property.list
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'property.list' has a clearly distinct purpose of listing Akamai CDN properties, and no other tools exist to cause confusion.
The naming pattern is perfectly consistent as there is only one tool. It follows a clear verb_noun structure ('property.list'), and with no other tools to compare against, there is no inconsistency in naming conventions.
A single tool is too few for a server intended to interact with Akamai's CDN properties, which typically involve operations like create, update, delete, or get details. This minimal set severely limits functionality and suggests an incomplete implementation for the domain.
The tool set is severely incomplete for managing Akamai CDN properties. It only provides listing functionality, missing essential CRUD operations such as create, read (get details), update, and delete, as well as other domain-specific actions like activating or deactivating properties, which are critical for a comprehensive CDN management surface.
Related MCP Connectors
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
327 dev tools via REST API and MCP. Generate Dockerfiles, schemas, K8s, APIs, and more.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseAqualityNot gradedmaintenanceEnables AI assistants to discover, retrieve details about, and manage MCP (Model Context Protocol) servers that provide additional tools and capabilities on demand.563 npm10-
- AlicenseNot gradedqualityDmaintenanceA collection of custom MCP servers providing various AI-powered capabilities including web search, YouTube video analysis, GitHub repository analysis, reasoning, code generation/execution, and web crawling.2MIT
- FlicenseNot gradedqualityDmaintenanceA MCP server that uses Amap API to provide location-based services, allowing users to get geographic information based on IP addresses and search for nearby points of interest.30-
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that provides deep knowledge about OpenAI APIs and SDKs, enabling users to query technical information through various MCP clients including ChatGPT Deep Research, Cursor, and OpenAI Responses API.15-