
Fastly
Fastly
README
Fastly API - Unofficial OpenAPI Specification
This repository contains an unofficial OpenAPI 3.0 specification for the Fastly API. It was created by reverse engineering the publicly available API documentation.
Disclaimer
This is an unofficial specification and is not endorsed, supported, or guaranteed by Fastly. It may be incomplete or contain inaccuracies. The specification is provided "as is" without warranty of any kind.
Features
- Comprehensive OpenAPI 3.0 schema for Fastly's CDN API
- Detailed endpoint descriptions and examples
- Schema definitions for request and response objects
- Support for all major Fastly API functionality:
- Service management
- Domain configuration
- Backend management
- VCL manipulation
- Cache controls
- Purging operations
- Edge dictionaries
- WAF security
- Logging endpoints
- Stats and metrics
- Compute@Edge
Specifications
This repository contains two OpenAPI specifications:
fastly-openapi.yaml
The complete specification of the Fastly API, containing all endpoints, parameters, and schemas. This is useful for comprehensive API documentation and client generation.
fastly-openapi-mcp.yaml
A streamlined subset of the API specifically optimized for AI agent interaction. This specification:
- Contains only the most frequently used endpoints for common Fastly tasks
- Focuses on the core operations needed for day-to-day management
- Maintains detailed descriptions and examples optimized for AI comprehension
- Prioritizes endpoints that are most useful in conversational interfaces
- Follows a task-based organization matching common user workflows
The MCP version is ideal for integration with AI assistants and tools that need to interact with Fastly through natural language interfaces.
Usage
Viewing Documentation
You can generate interactive documentation from these specifications using tools like:
Examples:
# For the complete API
npx @redocly/cli preview-docs fastly-openapi.yaml
# For the AI-optimized subset
npx @redocly/cli preview-docs fastly-openapi-mcp.yaml
Validation
To validate the specifications:
# For the complete API
npx @stoplight/spectral-cli lint fastly-openapi.yaml
# For the AI-optimized subset
npx @stoplight/spectral-cli lint fastly-openapi-mcp.yaml
Code Generation
These specifications can be used with OpenAPI code generators to create client libraries in various programming languages:
# For the complete API
npx @openapitools/openapi-generator-cli generate -i fastly-openapi.yaml -g javascript -o ./client
# For the AI-optimized subset
npx @openapitools/openapi-generator-cli generate -i fastly-openapi-mcp.yaml -g javascript -o ./client-mcp
Agent Readiness
Both specifications are designed to be "agent-ready" - optimized for use with AI agents and tools. They follow best practices for machine readability:
- Detailed operation descriptions
- Consistent naming patterns
- Complete schema documentation
- Examples for all operations
The MCP version takes agent-readiness even further with:
- Curated selection of high-value endpoints for common tasks
- Task-oriented organization aligned with user intents
- Enhanced descriptions focused on conversational contexts
- Removal of specialized endpoints that rarely appear in everyday usage
- Optimized for reduced token consumption in AI contexts
For specific use cases for the MCP specification, see subset.md which outlines common conversational tasks and the corresponding API workflows.
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.