Allows installation and distribution of the MCP server package through npm, enabling users to easily install or run the server using npm or npx commands.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Unleash Feature Flag MCP Server show me all feature flags in the dashboard project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This repository contains a Model Context Protocol (MCP) server for interacting with Unleash feature flag management system. It allows AI agents to manage feature flags through the Unleash API.
The Model Context Protocol (MCP) is a specification for enabling AI models to interact with external tools and data sources. This server implements the MCP protocol for Unleash, allowing AI assistants to manage feature flags programmatically.
Related MCP server: @shipeasy/mcp
You can install the package from npm:
npm install -g @ylin6/unleash-ff-mcp-serverOr run it directly using npx:
npx @ylin6/unleash-ff-mcp-serverThe server requires the following environment variables:
UNLEASH_API_URL: The URL of your Unleash API instance
UNLEASH_AUTH_TOKEN: The authentication token for your Unleash instance
The MCP server provides the following tools for managing feature flags:
Retrieves a list of all projects in the Unleash instance.
Retrieves all feature flags within a specific project.
Parameters:
projectId: The ID of the project
Creates a new feature flag within a project.
Parameters:
projectId: The ID of the project
name: The name of the feature flag
description: A description of the feature flag
type: The type of the feature flag (e.g., "release", "experiment", "operational", "kill-switch")
Updates an existing feature flag.
Parameters:
projectId: The ID of the project
featureId: The ID of the feature flag
description: A new description for the feature flag
type: A new type for the feature flag
Retrieves details about a specific feature flag.
Parameters:
projectId: The ID of the project
featureId: The ID of the feature flag
To use this MCP server with Cursor, use the following command in your cursor settings
env UNLEASH_API_URL=XXXX UNLEASH_AUTH_TOKEN=XXX npx -y @ylin6/unleash-ff-mcp-serverExample conversation with Cursor/Claude:
You: Show me all the feature flags in the 'dashboard' project
Claude: I'll fetch all the feature flags in the 'dashboard' project for you.
[Claude uses the getFeatures tool with projectId='dashboard']
Claude: Here are all the feature flags in the 'website' project:
- new-homepage (type: release)
- dark-mode (type: experiment)
- beta-footer (type: operational)
...To inspect the MCP server's operations, you can run:
npm run inspectThis uses the MCP inspector to analyze request/response patterns.
ISC
Create a new feature flag
Inputs: featureData (required), projectId (required).
Retrieve a specific feature flag from a project
Inputs: featureId (required), projectId (required).
Retrieve features for a specific project
Inputs: projectId (required).
Retrieve a list of projects
Inputs: no named parameters.
Update an existing feature flag
Inputs: featureData (required), featureId (required), projectId (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Every tool has a clearly distinct purpose with no overlap: createFeatureFlag and updateFeatureFlag handle modifications, getFeatureFlag and getFeatures retrieve specific or grouped data, and getProjects lists projects. The descriptions reinforce these distinctions, making misselection unlikely.
All tools follow a consistent verb_noun pattern with camelCase styling (e.g., createFeatureFlag, getFeatureFlag). There are no deviations in naming conventions, making the set predictable and easy to understand at a glance.
With 5 tools, the server is well-scoped for managing feature flags in Unleash. Each tool earns its place by covering essential operations: project listing, feature retrieval, and flag lifecycle management, without being overly sparse or bloated.
The toolset provides solid CRUD coverage for feature flags (create, get, update) and project listing, but lacks a deleteFeatureFlag tool, which is a minor gap. Agents can likely work around this, but the absence prevents full lifecycle management.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Feature flags, A/B experiments, kill switches, dynamic config & i18n — Shipeasy MCP server.
