This MCP server allows AI coding assistants to manage feature flags directly from the development environment without local installation. It integrates with tools like Cursor and Claude for streamlined feature flag management.
From the registry: DevCycle MCP server for feature flag management
Please install the `mcp-devcyclehq` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **DevCycle account** — Sign in via OAuth when first using the server (https://devcycle.com)
Canonical MCP server config (HTTP transport):
- url: `https://mcp.devcycle.com/mcp`
Note: Hosted MCP server; uses OAuth authentication on first use.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.DEVCYCLE_CLIENT_IDrequiredYour client ID for DevCycle API authorization.DEVCYCLE_CLIENT_SECRETrequiredYour client secret for DevCycle API authorization.DEVCYCLE_PROJECT_KEYrequiredThe project key for the DevCycle project.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.