MCP (Model Context Protocol) server for Featureflip — manage feature flags from AI coding assistants (Claude Code, Cursor, Copilot, Cline) and autonomous agents.
featureflip-mcp is an MCP project maintained in the canopy-labs/featureflip-mcp repository. The maintainer describes its purpose as “MCP (Model Context Protocol) server for Featureflip — manage feature flags from AI coding assistants (Claude Code, Cursor, Copilot, Cline) and autonomous agents”. Read the project documentation for the complete scope.
The documented npm package is @featureflip/mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares FEATUREFLIP_TOKEN. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"featureflip": {
"command": "npx",
"args": [
"-y",
"@featureflip/mcp"
],
"env": {
"FEATUREFLIP_TOKEN": "YOUR_FEATUREFLIP_TOKEN"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| FEATUREFLIP_TOKEN | Declared in the maintainer’s client configuration. | Check documentation |
Feature flags, A/B experiments, kill switches, dynamic config & i18n — Shipeasy MCP server.
Connect AI agents to CloudBees Unify: feature flags, CI/CD, release orchestration, and security
interacts with ConfigCat feature flag platform. Supports managing feature flags, configs, environments, products and organizations. Helps to
Manage ConfigDirector feature flags, remote configs, and targeting rules from AI assistants.
Manage DevCycle feature flags, inspect project settings and review flag evaluation counts through a hosted OAuth MCP connection.
Feature flags for Next.js. One file, full control with A/B testing.