Unleash

A Model Context Protocol (MCP) server implementation that integrates with Unleash Feature Toggle system.
  • typescript

10

GitHub Stars

typescript

Language

6 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": {
    "cuongtl1992-unleash-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "unleash-mcp"
      ],
      "env": {
        "UNLEASH_URL": "YOUR_UNLEASH_END_POINT",
        "MCP_HTTP_PORT": "3001",
        "MCP_TRANSPORT": "stdio",
        "UNLEASH_API_TOKEN": "YOUR_UNLEASH_API_TOKEN"
      }
    }
  }
}

You can connect LLM applications to Unleash feature flags through the MCP server, enabling you to check, expose, create, update, and list features and projects directly from your AI workflows. This bridge makes feature flag data available to models and automates flag-driven decisions across your applications.

How to use

You run the MCP server locally and connect your MCP client to it. The Unleash MCP Server exposes a standard MCP interface that lets your LLM-powered workflows query the status of feature flags, create or update flags, and list projects. Use this to tailor AI behavior based on real-time feature configurations and project scopes.

How to install

Prerequisites you need before installing the server:

  • Node.js v18 or higher
  • TypeScript v5.0 or higher
  • Access to an Unleash server instance

Install dependencies and prepare the server for runtime:

# Install dependencies
npm i

# Compile TypeScript (if applicable)
npm run build

# Start the server
npm start

Configuration and startup

The server can be started via a local MCP command configuration. The following snippet shows how to run the Unleash MCP Server as an MCP stdio process, which starts the server and exposes an MCP transport over stdio.

{
  "mcpServers": {
    "unleash": {
      "command": "npx",
      "args": [
        "-y",
        "unleash-mcp"
      ],
      "env": {
        "UNLEASH_URL": "YOUR_UNLEASH_END_POINT",
        "UNLEASH_API_TOKEN": "YOUR_UNLEASH_API_TOKEN",
        "MCP_TRANSPORT": "stdio",
        "MCP_HTTP_PORT": 3001
      }
    }
  }
}

Available tools

getFlag

Retrieve the status and properties of a specific Unleash feature flag via MCP.

getProjects

List all Unleash projects.

flagCheck

Check the status of a single feature flag within an MCP prompt.

batchFlagCheck

Check multiple feature flags in a single batch request for a given context.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational