CLI / MCP Overview
DevCycle provides two complementary tools for managing feature flags: a command-line interface for developers and an MCP server for use with AI assistants.
DevCycle CLI
The DevCycle CLI is a comprehensive command-line tool for feature flag management.
Key Features
- Feature Flag Management: Create, update, and delete feature flags
- Environment Control: Manage targeting across different environments
- Project Administration: Switch between projects and manage settings
- Integration Ready: Perfect for automation and CI/CD workflows
- Local Development: Test and validate flags locally
Quick Start
- Install:
npm install -g @devcycle/cli
- Login:
dvc login sso
- Select project:
dvc projects select
- Start using CLI commands like:
dvc features list
Explore CLI Reference → | View CLI User Guides →
DevCycle MCP Server
The DevCycle MCP Server is based on our CLI and enables AI assistants like Claude Desktop, Cursor, and other MCP-compatible clients to directly interact with your DevCycle feature flags, environments, and projects through natural language.
Example interactions:
- "Create a new feature flag called 'new-checkout-flow'"
- "Enable targeting for my-feature in production"
- "An incident occurred at 5pm today, show me what changes happened within the hour before the incident"
What is MCP?
The Model Context Protocol (MCP) is an open standard that enables AI applications to securely connect to data sources and tools. DevCycle's MCP server acts as a bridge between AI assistants and your feature flag management, allowing you to:
- Create and manage feature flags using natural language
- Configure targeting rules without writing complex queries
- Test features safely using self-targeting and overrides
- Get real-time insights about your feature flag usage
Key Benefits
- Natural Language Interface: Use commands like "Create a feature flag for the new checkout flow"
- Production Safety: Built-in warnings and confirmations for destructive actions
- Comprehensive Coverage: 35+ tools across all DevCycle operations
Get Started with MCP → | MCP Reference →
Choose Your Workflow
Tool | Best For |
---|---|
CLI | Direct command-line control, scripting, CI/CD integration |
MCP | Natural language interactions, AI-assisted development |
Both tools use the same DevCycle APIs and can be used together seamlessly.
Getting Help
- Community: Discord
- Issues: GitHub
- Support: Contact Us