How to Use the LaunchDarkly MCP in Windsurf

Q: Can I use Windsurf to track down who changed a LaunchDarkly targeting rule?

Yes, Cascade handles this. It queries listauditlogs to fetch the history of your account changes, matching the timestamp of the break with the specific team member who modified the rule.

Q: How do I configure the LaunchDarkly connection in Windsurf?

Add the MCP Server to your mcpconfig.json file under the mcpServers block. Once saved, Windsurf auto-discovers all nine tools, making them immediately available to Cascade.

Let Windsurf autonomously map your LaunchDarkly feature flags and audit logs to resolve production issues without manual prompting.

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 Windsurf

Create your Vinkius account to connect LaunchDarkly to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Windsurf Chains Flag Diagnostics Autonomously

Windsurf uses `list_projects` and `list_environments` to map out your workspaces the second a bug hits. Cascade doesn't wait for your permission to check each environment; it immediately targets the broken LaunchDarkly pipeline. Once it finds the target environment, the agent automatically triggers `list_feature_flags` to pinpoint recent toggles. This MCP integration means you don't have to type a single follow-up command to get a complete map of your active configurations.

Audit Trails Handled by the MCP Server

This server calls `list_audit_logs` to retrieve your team's configuration changes directly inside Cascade. Tracking down who flipped a toggle shouldn't require manual digging or jumping between your browser and the editor. Instead of hunting down commits, you get the exact author and flag change side by side. Cascade analyzes the payload from `get_feature_flag` to verify if a targeting rule change caused the sudden spike in errors.

Metric Validation During Deployments

The integration calls `list_metrics` and `get_metric` to monitor your active experiment variations. Cascade monitors your system health while you roll out new code without context switching. Using this MCP Server, you set the target and the agent keeps watch. If a metric dips, the agent inspects the setup through `get_environment` to identify the drift.

Setup guide

Set up LaunchDarkly MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my LaunchDarkly payment history." If connected, Cascade will call the LaunchDarkly tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "launchdarkly-mcp": {
      "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 Windsurf

Windsurf uses Cascade to chain tools without your manual input. It runs `list_feature_flags` to find matching toggles and then calls `get_feature_flag` to verify targeting rules in one go.

Yes, Cascade handles this. It queries `list_audit_logs` to fetch the history of your account changes, matching the timestamp of the break with the specific team member who modified the rule.

It does. Cascade lists all your environments and workspaces by combining `list_projects` and `list_environments` to build a clean directory of your active configurations.

Add the MCP Server to your `mcp_config.json` file under the `mcpServers` block. Once saved, Windsurf auto-discovers all nine tools, making them immediately available to Cascade.

This server only touches flag states, project metadata, and audit logs. The data is handled inside a secure, ephemeral V8 sandbox, ensuring your workspace tokens are never cached or exposed to external servers.

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