Devcycle Release Notes

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

These instructions use the remote DevCycle MCP server. For installation of the local MCP server, see the reference docs.

Configure Your AI Client

Tabs for Cursor, VS Code, Claude Code, Claude Desktop, Windsurf, Codex CLI, Gemini CLI

Cursor tab content:

To open Cursor and automatically add the DevCycle MCP, click the install button above. Alternatively, add the following to your ~/.cursor/mcp_settings.json file. To learn more, see the Cursor documentation.

{
  "mcpServers": {
    "DevCycle": {
      "url": "https://mcp.devcycle.com/mcp"
    }
  }
}

Authentication in Cursor:

1. After configuration, you'll see DevCycle MCP listed as "Needs login" with a yellow indicator
2. Click on the DevCycle MCP server to initiate the authorization process
3. This opens a browser authorization page at mcp.devcycle.com
4. Review and click "Allow Access" to grant permissions
5. If you have multiple organizations, select your desired organization at auth.devcycle.com
6. You'll be redirected back to Cursor with the server now active

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 list_projects, 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
• CLI Reference - Learn about the underlying CLI commands

Getting Help

• GitHub Issues: GitHub Issues
• General Documentation: DevCycle Docs
• DevCycle Community: Discord
• Support: Contact Support

Original source Report a problem

AI Generated Schemas

We're really excited to announce some new AI-assisted functionality in the DevCycle Dashboard. These tools are designed to make life easier and simplify the creation of critical objects in the DevCycle platform.

💂 AI Generated Schemas
Variable Schemas are a great tool for protecting production. They set guardrails for a given Variable allowing only certain values to be set when modifying a Feature's configuration. The problem is, Variable Schemas can be complex to create.
With AI Generated Schemas we've made the initial creation of Schemas extremely simple. AI looks at the Variable values you've already set for a feature and creates a Schema that validates against those current values. From there you can edit the Schema as needed based on your preferences.
Check out our docs to get started with AI Generated Schemas

AI Generated Feature Summaries

We all want to keep our teammates informed about what a Feature controls, but it can be tedious to keep descriptions, summaries or internal Wikis up to date.
This is why we created AI Generated Feature Summaries. With this tool, AI distills down a Feature's current configuration and provides a detailed point-in-time summary that you can then augment as needed. This makes it extremely easy to keep summaries fresh.

Original source Report a problem

We're really excited to announce some new AI-assisted functionality in the DevCycle Dashboard. These tools are designed to make life easier and simplify the creation of critical objects in the DevCycle platform.

💂 AI Generated Schemas

Variable Schemas are a great tool for protecting production. They set guardrails for a given Variable allowing only certain values to be set when modifying a Feature's configuration. The problem is, Variable Schemas can be complex to create.
With AI Generated Schemas we've made the initial creation of Schemas extremely simple. AI looks at the Variable values you've already set for a feature and creates a Schema that validates against those current values. From there you can edit the Schema as needed based on your preferences.
Check out our docs to get started with AI Generated Schemas

📋 AI Generated Feature Summaries

We all want to keep our teammates informed about what a Feature controls, but it can be tedious to keep descriptions, summaries or internal Wikis up to date.
This is why we created AI Generated Feature Summaries. With this tool, AI distills down a Feature's current configuration and provides a detailed point-in-time summary that you can then augment as needed. This makes it extremely easy to keep summaries fresh.

Original source Report a problem

Send DevCycle Feature changes and runtime evaluations into Dynatrace so your teams can easily monitor app performance tied to flags.

• Feature change events (targeting/variation updates) stream into Dynatrace using predefined workflows
• Flag evaluation traces from your apps via SDK hooks (captured by OneAgent)
• Prebuilt Dynatrace dashboard to investigate anomalies alongside feature context
• Environment mapping to keep DevCycle and Dynatrace in sync

This integration adds feature flag evaluation data to your traces, helping with faster debugging, tracking rollbacks, and shipping with confidence!

Check out our docs to learn more!

Original source Report a problem

Dynatrace Integration

• Feature change events (targeting/variation updates) stream into Dynatrace using predefined workflows
• Flag evaluation traces from your apps via SDK hooks (captured by OneAgent)
• Prebuilt Dynatrace dashboard to investigate anomalies alongside feature context
• Environment mapping to keep DevCycle and Dynatrace in sync

This integration adds feature flag evaluation data to your traces, helping with faster debugging, tracking rollbacks, and shipping with confidence!

Check out our docs to learn more!

Original source Report a problem

We're really excited to announce the availability of the ✨ DevCycle MCP Server ✨

We've been hard at work to make sure the tools and prompts are intuitive and can work naturally in your workflow.

The DevCycle MCP Server is great to:

• Create Features and their associated Variables directly from your IDE
• QA Features by managing overrides through chat
• Investigate and Report on Incidents by getting all audit log details within a given time range
• Remove Flags easily by converting all Variables associated with Completed Features into static code

You can install either the Remote or Local MCP Server depending on your needs and use cases.

Check out the docs for one-click install into Cursor or VS Code

Original source Report a problem

DevCycle MCP Server Availability

We're really excited to announce the availability of the ✨DevCycle MCP Server ✨

We've been hard at work to make sure the tools and prompts are intuitive and can work naturally in your workflow.

The DevCycle MCP Server is great to:

• Create Features and their associated Variables directly from your IDE
• QA Features by managing overrides through chat
• Investigate and Report on Incidents by getting all audit log details within a given time range
• Remove Flags easily by converting all Variables associated with Completed Features into static code

You can install either the Remote or Local MCP Server depending on your needs and use cases.

Check out the docs for one-click install into Cursor or VS Code

Original source Report a problem

Evaluation object for variable evaluations

We’ve added a new eval object to all variable evaluations, making it easier than ever to debug and understand why a specific value was returned for a user.

Each Variable evaluation now includes:

• reason – the primary reason a value was served (e.g. TARGETING_MATCH, DEFAULT, SPLIT, etc.)
• details – optional context for why the match occurred
• target_id – the rule or audience that matched, when applicable

These values are especially useful for debugging, QA, building custom logs and observability workflows.

⚠️ Heads up: the older evalReason field is now deprecated and will be removed in an upcoming release. Please update your SDK usage to rely on the new eval object instead.

Learn more about evaluation reasons in the docs: https://docs.devcycle.com/sdk/features#evaluation-reasons

Original source Report a problem

We’ve added a new eval object to all variable evaluations, making it easier than ever to debug and understand why a specific value was returned for a user.

Each Variable evaluation now includes:

• reason – the primary reason a value was served (e.g. TARGETING_MATCH, DEFAULT, SPLIT, etc.)
• details – optional context for why the match occurred
• target_id – the rule or audience that matched, when applicable

These values are especially useful for debugging, QA, building custom logs and observability workflows.

⚠️ Heads up: the older evalReason field is now deprecated and will be removed in an upcoming release. Please update your SDK usage to rely on the new eval object instead.

Learn more about evaluation reasons in the docs: https://docs.devcycle.com/sdk/features#evaluation-reasons

Original source Report a problem