MCP Server Integration

Integrate Featureflow with AI assistants like Claude, Cursor, and other MCP-compatible tools. The Featureflow MCP server enables AI assistants to manage your feature flags, projects, environments, and more through natural language.

GitHub: https://github.com/featureflow/featureflow-mcp

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI assistants to interact with external tools and services. With the Featureflow MCP server, you can ask your AI assistant to:

• List and search feature flags
• Create, update, and delete features
• Enable or disable features in specific environments
• Manage projects and environments
• View targeting rules and API keys

Quick Start

1. Create a Personal Access Token

1. Log into Featureflow as an administrator
2. Navigate to Administration → API Tokens
3. Click Create Token and copy the token (starts with api-)

2. Configure in Cursor

Add to your ~/.cursor/mcp.json:

{
  "mcpServers": {
    "featureflow": {
      "command": "npx",
      "args": ["-y", "featureflow-mcp"],
      "env": {
        "FEATUREFLOW_API_TOKEN": "api-your-token-here"
      }
    }
  }
}

3. Restart Cursor

Press Cmd+Shift+P → "MCP: Restart Servers" or restart Cursor.

That's it! You can now ask Claude to manage your feature flags.

Configuration

Environment Variable	Description
FEATUREFLOW_API_TOKEN	Personal Access Token (required)

Available Tools

Projects

Tool	Description
list_projects	List all projects, optionally filtered by query
get_project	Get a specific project by ID or key
create_project	Create a new project
update_project	Update an existing project
delete_project	Delete a project

Features

Tool	Description
list_features	List features with optional filters
get_feature	Get a specific feature by ID or unified key
create_feature	Create a new feature flag
update_feature	Update an existing feature
clone_feature	Clone a feature with a new key
archive_feature	Archive or unarchive a feature
delete_feature	Delete a feature

Feature Controls

Tool	Description
get_feature_control	Get feature control settings for an environment
update_feature_control	Enable/disable features, modify rules

Environments

Tool	Description
list_environments	List environments for a project
get_environment	Get a specific environment
create_environment	Create a new environment
update_environment	Update an existing environment
delete_environment	Delete an environment

Targets & API Keys

Tool	Description
list_targets	List targeting attributes for a project
get_target	Get a specific target by key
list_api_keys	List SDK API keys for an environment

Example Usage

Once configured, you can ask your AI assistant things like:

• "List all my Featureflow projects"
• "Create a feature called 'new-checkout' in the 'webapp' project"
• "Enable the 'dark-mode' feature in production"
• "What features are currently enabled in staging?"
• "Disable 'beta-feature' in all environments"
• "Show me the targeting rules for 'premium-feature'"
• "Clone 'existing-feature' to 'new-feature-v2'"

Troubleshooting

MCP Server Not Connecting

1. Verify your API token is correct and starts with api-
2. Ensure the token has the correct permissions
3. Check that npx is available in your PATH
4. Restart your AI assistant after configuration changes

Permission Errors

The API token must have sufficient permissions for the operations you're requesting. Contact your Featureflow administrator if you need elevated access.

License

MIT - see LICENSE for details.