How to Use the LaunchDarkly MCP in Claude Code

Q: How do I add this tool to my Claude Code setup?

Run the claude mcp add command in your terminal, specifying the transport type and the server connection URL. Verify the installation using claude mcp list to register the MCP Server in your config.

Execute headless LaunchDarkly configurations and audit checks directly from your terminal using Claude Code pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LaunchDarkly MCP to Claude Code

Create your Vinkius account to connect LaunchDarkly 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 LaunchDarkly with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claude Code Drives Headless Flag Auditing

Claude Code executes `list_audit_logs` and `get_feature_flag` to pipe configuration states straight to your stdout. Run audits directly from your shell without opening a browser or clicking through a UI. It is built for terminal speed. You can easily script the agent to check flag schemas before a deployment to make sure your staging and production toggles match perfectly.

CI/CD Environment Verification via MCP Server

The CLI agent uses `list_environments` and `get_environment` to verify target parameters before running builds. This MCP Server lets your CLI agent verify target environments before starting a container build. If the environment variables don't match the active settings, the agent halts the pipeline. This prevents configuration drift from reaching your live production servers.

Terminal-Based Metric and Experimentation Tracking

This integration queries `list_metrics` and `get_metric` to output real-time experimentation data directly to your shell. Monitor your experiment performance without leaving your terminal session. This MCP integration formats the output as clean text that you can immediately redirect to other terminal tools. This makes it simple to run quick checks on metric health during an active SSH session.

Setup guide

Set up LaunchDarkly 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 launchdarkly-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http launchdarkly-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 LaunchDarkly 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": {
    "launchdarkly-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 LaunchDarkly. 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 LaunchDarkly 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 LaunchDarkly MCP in Claude Code

Yes. You can pipe Claude Code outputs to grep or other terminal utilities by querying `list_audit_logs` directly from the CLI.

Run the agent in your terminal and ask it to check your setups. It will call `list_environments` and `get_environment` to output the exact status of your project.

Yes, it does. The CLI agent can execute multi-step scripts, calling `list_projects` and `list_feature_flags` to automate configuration checks before you trigger a deploy.

Run the `claude mcp add` command in your terminal, specifying the transport type and the server connection URL. Verify the installation using `claude mcp list` to register the MCP Server in your config.

The integration only reads flag configurations, metric values, and environment metadata. All operations run inside Vinkius's isolated, ephemeral V8 sandbox, ensuring your API key is never exposed to the shell environment or stored locally.

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