Use LaunchDarkly’s self-managed MCP server for documented EU and federal environments, with feature flag, environment and AI configuration tools.
LaunchDarkly’s local MCP server is the self-managed option documented for its EU and federal environments. It exposes supported feature-management operations, including flags and environment-related configuration. The maintainer recommends the separately hosted service where that service is available.
Specify the project, flag and environment before asking about targeting or variations. Read the existing configuration before proposing a rollout change. Keep the environment visible in the result, because changing a development flag and changing a production flag are different operations.
The npm package is @launchdarkly/mcp-server; --package in the launch example is an npx option, not a package identifier. Follow the README’s full launch arguments and API-key instructions. The --server-url option selects the documented LaunchDarkly environment. Choose this local profile when its regional deployment model matches the account.
Maintainer’s setup and tool reference. Browse feature flags MCP servers for related workflows.
A LaunchDarkly API token and the current full launch arguments for the intended EU or federal environment.
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.
MCP (Model Context Protocol) server for Featureflip — manage feature flags from AI coding assistants (Claude Code, Cursor, Copilot, Cline) and autonomous agents.