How to Use the DevCycle MCP in Claude Code

Q: How do I add the DevCycle MCP Server to Claude Code?

Run the claude mcp add command in your terminal, specifying the HTTP transport. Once connected, Claude Code immediately registers tools like listfeatureflags for your CLI sessions.

Q: How does Claude Code search through large lists of DevCycle flags?

The agent uses searchfeatureflags to query the API directly with your keywords. It avoids dumping thousands of lines into your terminal by filtering the results before displaying them.

Q: Can I view SDK keys for my builds using this terminal agent?

Yes. You can ask the agent to run getenvironmentsdkkeys for a specific project. It will output the keys directly to your terminal, making it easy to copy them into your local config files.

Manage DevCycle flags and audit environments directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevCycle MCP to Claude Code

Create your Vinkius account to connect DevCycle to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DevCycle with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-driven flag ops with this MCP Server

To view your entire release setup from the terminal, the agent runs `list_devcycle_projects` to fetch your projects. Claude Code lets you query your entire release setup using simple commands, letting you switch contexts instantly without leaving your shell. Once you select a project, the agent calls `list_project_environments` to display your deployment targets. You get a clean, text-based overview of Staging and Production environments piped directly into your terminal.

Fast pipeline targeting verification

Before running CI/CD scripts, Claude Code uses `get_environment_sdk_keys` to pull the keys required for your build pipelines. It verifies that your environment variables match your active DevCycle configurations without exposing raw keys to your shell history. To double-check targeting rules, the agent runs `get_feature_flag_details` to output the JSON payload of your active rules. You can quickly inspect who sees what, ensuring your staging environment matches your expectations before a deploy.

Instant status toggles via CLI

When a production incident occurs, you can toggle flags instantly by running `update_feature_flag_status` from your command prompt. You don't have to navigate a browser UI while production is throwing errors. The agent can search for the problematic flag using `search_feature_flags`, verify its current state with `list_active_flags`, and flip the switch immediately. It is the fastest way to execute a rollback using this MCP Server.

Setup guide

Set up DevCycle MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see devcycle-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest DevCycle transactions." It will automatically discover and invoke the available DevCycle tools.

Terminal

claude mcp add --transport http devcycle-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the DevCycle MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "devcycle-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DevCycle. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DevCycle now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DevCycle MCP in Claude Code

Run the `claude mcp add` command in your terminal, specifying the HTTP transport. Once connected, Claude Code immediately registers tools like `list_feature_flags` for your CLI sessions.

Yes. Because Claude Code runs entirely in the terminal, you can ask it to run `update_feature_flag_status` as part of a post-deployment shell script or automated release sequence.

The agent uses `search_feature_flags` to query the API directly with your keywords. It avoids dumping thousands of lines into your terminal by filtering the results before displaying them.

Yes. You can ask the agent to run `get_environment_sdk_keys` for a specific project. It will output the keys directly to your terminal, making it easy to copy them into your local config files.

Absolutely. All interactions with your feature variables and environment keys are executed over secure HTTPS connections. The Vinkius MCP runtime enforces strict zero-trust isolation, ensuring your API payloads never persist on disk or leak into shell telemetry.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript