DevCycle
officialTurn your favourite AI tool into a feature management assistant. DevCycle's MCP works with your favourite coding assistant so you can create and monitor feature flags using natural language right in your workflow.
What can you do with DevCycle MCP?
- Create and manage feature flags — Ask your assistant to create a new feature flag, list existing features, update or delete them, or review a feature's audit log history.
- Manage feature variables — List, create, update, and delete the variables attached to your feature flags.
- Switch and inspect projects — Select which DevCycle project to work in and view details about the currently selected project.
- Set self-targeting overrides — View your targeting identity, set or list overrides, and clear a feature's overrides for testing.
- Check evaluation analytics — Retrieve total evaluation counts for a specific feature or an entire project.
- Get SDK install guidance — Ask for SDK installation instructions and examples for your project.
Documentation
The DevCycle Model Context Protocol (MCP) Server is based on the DevCycle CLI and enables AI coding tools like Claude Code and Cursor, or general-purpose tools like Claude Desktop, to interact directly with your DevCycle projects and make changes on your behalf.
Quick Setup
The DevCycle MCP is hosted so there is no need to set up a local server. We'll walk you through installation and authentication with your preferred AI tools.
Direct Connection: For clients that natively support the MCP specification with OAuth authentication, you can connect directly to our hosted server:
https://mcp.devcycle.com/mcp
Protocol Support: Our MCP server supports both SSE and HTTP Streaming protocols, automatically negotiating the best option based on your client's capabilities.
Alternative Endpoint: If your client has issues with protocol negotiation, use the SSE-only endpoint:
https://mcp.devcycle.com/sse
MCP Registry: If you're using registry.modelcontextprotocol.io, the DevCycle MCP is listed as: com.devcycle/mcp
[!-info] -info info
These instructions use the remote DevCycle MCP server. For installation of the local MCP server, see the reference docs.
Configure Your AI Client
- Claude Code
- Claude Desktop
- Codex CLI
- Codex App
- Cursor
- VS Code
- OpenCode
- Antigravity CLI
- Devin Desktop
Step 1: Add DevCycle MCP Server
Run the following command in your terminal:
claude mcp add --transport http devcycle https://mcp.devcycle.com/mcp
Step 2: Manage MCP Connection
Start Claude Code and enter the MCP management interface:
/mcp
Step 3: Authentication
You'll see the DevCycle server listed as "Needs authentication":
- Select the DevCycle server and press Enter to authenticate
- This will open a browser page at
mcp.devcycle.comfor authorization - Review and click "Allow Access" to grant permissions
- If you have multiple organizations, select your desired organization at
auth.devcycle.com - Return to Claude Code where the server will show as connected
For more details, see the Claude Code MCP documentation.
Available Tools
The DevCycle MCP Server provides comprehensive feature flag management tools organized into 6 categories:
| Category | Tools | Description |
|---|---|---|
| Feature Management | list_features, create_feature, update_feature, update_feature_status, delete_feature, cleanup_feature, get_feature_audit_log_history | Create and manage feature flags |
| Variable Management | list_variables, create_variable, update_variable, delete_variable | Manage feature variables |
| Project Management | get_current_project, select_project | Project selection and details |
| Self-Targeting & Overrides | get_self_targeting_identity, update_self_targeting_identity, list_self_targeting_overrides, set_self_targeting_override, clear_feature_self_targeting_overrides | Testing and overrides |
| Results & Analytics | get_feature_total_evaluations, get_project_total_evaluations | Usage analytics |
| SDK Installation | install_devcycle_sdk | SDK install guides and examples |
Try It Out
Once configured, try asking your AI assistant:
- "Create a new feature flag called 'new-checkout-flow'"
- "List all features in my project"
- "Enable targeting for the header-redesign feature in production"
- "Show me evaluation analytics for the last 7 days"
Next Steps
- MCP Reference - Complete tool documentation with all parameters
- - Learn about the underlying CLI commands
Getting Help
- GitHub Issues: GitHub Issues
- General Documentation: DevCycle Docs
- Support: Contact Support