Unleash

Provides an experimental MCP server that validates, analyzes, and wraps Unleash feature flags for AI-assisted development.

typescript

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "unleash-unleash-mcp": {
      "command": "npx",
      "args": [
        "unleash-mcp",
        "--log-level",
        "debug"
      ],
      "env": {
        "UNLEASH_PAT": "YOUR_PAT_TOKEN",
        "UNLEASH_BASE_URL": "https://your-unleash-instance.example.com",
        "UNLEASH_DEFAULT_PROJECT": "default-project"
      }
    }
  }
}

This MCP server provides focused tooling to create, evaluate, and wrap feature flags for Unleash in an automated workflow. It guides you through validating flag needs, detecting existing flags to prevent duplication, and generating language-specific wrapping code for safe, best-practice deployments.

How to use

To use the MCP server with an MCP client, first ensure you have access to an Unleash instance and a valid personal access token. You will run the MCP server in conjunction with your editor or CI workflow to assess changes, decide on flag usage, and generate the necessary wrapping code.

How to install

Prerequisites include Node.js 18 or higher and a package manager such as npm or Yarn. You also need access to an Unleash instance and a personal access token.

# Quick start with a local, standalone MCP server
UNLEASH_BASE_URL={{your-instance-url}} \
UNLEASH_PAT={{your-personal-access-token}} \
UNLEASH_DEFAULT_PROJECT={{default_project_id}} \
npx unleash-mcp --log-level debug

Notes for local development and agent integration are provided in the following practical paths.

Available tools

create_flag

Creates a new feature flag in Unleash with validation and progress tracking.

evaluate_change

Evaluates whether a code change should be behind a feature flag, including risk assessment and guidance.

detect_flag

Finds existing feature flags to encourage reuse and prevent duplicates.

wrap_change

Generates language-specific code to wrap changes with a feature flag.

set_flag_rollout

Configures rollout strategies for a feature flag without enabling it.

get_flag_state

Retrieves a flag's metadata and activation strategies.

toggle_flag_environment

Enables or disables a feature flag in a given environment.

remove_flag_strategy

Deletes a flag's strategy from an environment.

cleanup_flag

Generates instructions for safely removing flagged code paths.

Built by

VeilStrat

AI signals for GTM teams