Unleash
MCP server for managing Unleash feature flags and automate best practices.
Ads
Overview
A purpose-driven Model Context Protocol (MCP) server for managing Unleash feature flags. This server enables LLM-powered coding assistants to create and manage feature flags following Unleash best practices. To share feedback, join our community Slack or open an issue on GitHub. This MCP server provides tools that integrate with the Unleash Admin API, allowing AI coding assistants to: - Create feature flags with proper validation and typing. - Detect existing flags to prevent duplicates or encourage reuse. - Evaluate changes to decide when a feature flag is needed. - Stream progress for visibility during operations. - Handle errors gracefully with helpful hints. - Follow best practices from the Unleash documentation.
Installation
claude mcp add unleash --env UNLEASH_BASE_URL={{your-instance-url}} --env UNLEASH_PAT={{your-personal-access-token}} -- npx -y @unleash/mcp@latest --log-level errorConfiguration
Configuration example is not available yet.
Capabilities
- Create feature flags
Ask the assistant to create a new flag with `create_flag`, specifying name, type, and description.
- Evaluate if a change needs a flag
Use `evaluate_change` to assess risk and get a recommendation before modifying code.
- Detect existing flags to avoid duplicates
Run `detect_flag` to search the codebase for flags that already cover your use case.
- Get code wrapping guidance
After creating a flag, use `wrap_change` to generate language-specific snippets for implementing it.
- Configure gradual rollouts
Set rollout percentage and stickiness with `set_flag_rollout` before enabling a flag.
- Toggle flags and manage strategies
Enable or disable flags via `toggle_flag_environment`, remove strategies with `remove_flag_strategy`, and inspect state with `get_flag_state`.
Tags
- devops
- deployment
- development
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.