MCP server from flipt-io/mcp-server-flipt
- • Core MCP protocol features implemented (25/40)
- • Room for improvement in GitHub community
- • Optimal dependency management (20/20)
- • Moderate deployment maturity (5/10)
- • Documentation (8/8)
- • Archestra MCP Trust score badge is missing
{
"flipt-io-mcp-server-flipt-global": {
"command": "mcp-server-flipt",
"args": [],
"env": {}
},
"flipt-io-mcp-server-flipt-npx": {
"command": "npx",
"args": [
"-y",
"@flipt-io/mcp-server-flipt"
],
"env": {}
},
"flipt-io-mcp-server-flipt-docker": {
"command": "docker",
"args": [
"run",
"-d",
"--name",
"mcp-server-flipt",
"ghcr.io/flipt-io/mcp-server-flipt:latest"
],
"env": {},
"docker_image": "ghcr.io/flipt-io/mcp-server-flipt:latest"
},
"flipt-io-mcp-server-flipt-npm-start": {
"command": "npm",
"args": [
"start"
],
"env": {}
}
}Flipt MCP Server
A Model Context Protocol (MCP) server for Flipt, allowing AI assistants to interact with feature flags.
Features
- List, create, update, and delete namespaces, flags, segments, rules, and more
- Evaluate flags for specific entities
- Toggle flags on/off
- Manage constraints, variants, distributions, and rollouts
Usage
Once the server is running, it will:
- Set up a STDIO transport for MCP communication
- Register tools and prompts for interacting with Flipt
The server is designed to be used with AI assistants that support the Model Context Protocol.
Installing via Smithery
To install Flipt MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @flipt-io/mcp-server-flipt --client claude
Node
You can install the package globally and run it:
npm install -g @flipt-io/mcp-server-flipt && mcp-server-flipt
Or run it directly with npx:
npx -y @flipt-io/mcp-server-flipt
Docker
You can also run the server in a Docker container:
docker run -d --name mcp-server-flipt ghcr.io/flipt-io/mcp-server-flipt:latest
Configuration
The server can be configured using environment variables:
FLIPT_API_URL: The URL of the Flipt API (default: http://localhost:8080)FLIPT_API_KEY: The API key to use for the Flipt API (optional)
You can set these in a .env file in the directory where you run the server.
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build the project
npm run build
# Start the server
npm start
# Format code
npm run fmt
# Lint code
npm run lint
License
Apache 2.0
[](https://archestra.ai/mcp-catalog/flipt-io__mcp-server-flipt)Flipt MCP Server
A Model Context Protocol (MCP) server for Flipt, allowing AI assistants to interact with feature flags.
Features
- List, create, update, and delete namespaces, flags, segments, rules, and more
- Evaluate flags for specific entities
- Toggle flags on/off
- Manage constraints, variants, distributions, and rollouts
Usage
Once the server is running, it will:
- Set up a STDIO transport for MCP communication
- Register tools and prompts for interacting with Flipt
The server is designed to be used with AI assistants that support the Model Context Protocol.
Installing via Smithery
To install Flipt MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @flipt-io/mcp-server-flipt --client claude
Node
You can install the package globally and run it:
npm install -g @flipt-io/mcp-server-flipt && mcp-server-flipt
Or run it directly with npx:
npx -y @flipt-io/mcp-server-flipt
Docker
You can also run the server in a Docker container:
docker run -d --name mcp-server-flipt ghcr.io/flipt-io/mcp-server-flipt:latest
Configuration
The server can be configured using environment variables:
FLIPT_API_URL: The URL of the Flipt API (default: http://localhost:8080)FLIPT_API_KEY: The API key to use for the Flipt API (optional)
You can set these in a .env file in the directory where you run the server.
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build the project
npm run build
# Start the server
npm start
# Format code
npm run fmt
# Lint code
npm run lint
License
Apache 2.0
Related MCP Servers
Agent-MCP
89/100Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for developers building AI applications that benefit from multiple specialized agents working in parallel on different aspects of a project.
serena
85/100A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
JFrog MCP Server
85/100Official JFrog MCP server that enables AI assistants to interact with the JFrog Platform. Supports repository management, build tracking, runtime monitoring, artifact searching, package intelligence, and Xray security scanning.
context7
82/100Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
gk-cli
81/100GitKraken CLI Releases and Documentation
Excalidraw
80/100Remote MCP server for Excalidraw - streams hand-drawn diagrams with smooth viewport camera control and interactive fullscreen editing

