How to Use the Unleash (Feature Toggles) MCP in Claude Code

Q: Can I list all available projects and environments in Claude Code?

Absolutely. Use listprojects to get every project ID, then run listenvironments to see which deployment stages are configured for the release pipeline.

Q: What if my CI job needs feature flags for a specific user group using Unleash (Feature Toggles) and Claude Code?

You can use getfrontendfeatures, passing the necessary context like a segment ID or project ID. This ensures your automated tests run against the correct set of toggles.

Q: How do I verify all available user accounts for an audit using Unleash (Feature Toggles) and Claude Code?

Run listusers to pull a comprehensive list of every configured account. This is critical before running automated security scans or access checks.

Automate feature flag checks in CI/CD pipelines with Claude Code's headless terminal execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unleash (Feature Toggles) MCP to Claude Code

Create your Vinkius account to connect Unleash (Feature Toggles) 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 Unleash (Feature Toggles) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute environment-specific evaluations

When writing a shell script or Docker build step, you need reliability. The `get_client_features` tool fetches active feature flags and strategies for the current deployment context. This means your CI job only proceeds if the necessary toggle is live. You can also use `list_environments` to verify that the pipeline is running against the intended target environment before deploying anything.

Batch list all required metadata

For infrastructure checks, you need a full inventory. Running `list_projects` pulls every Unleash project ID for scope checking. Similarly, `list_segments` gives you a manifest of all configured user segments. Claude Code can script the collection of these lists to validate deployment prerequisites.

Manage and report metrics headless

In an automated pipeline, logging is key. You use `report_client_metrics` or `report_frontend_metrics` to send usage data without needing a GUI. Plus, you can use `register_client` if the script needs to authenticate as a new backend SDK instance. This guarantees that flag adoption metrics are captured even during headless runs.

Setup guide

Set up Unleash (Feature Toggles) 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 unleash-feature-toggles-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Unleash (Feature Toggles) transactions." It will automatically discover and invoke the available Unleash (Feature Toggles) tools.

Terminal

claude mcp add --transport http unleash-feature-toggles-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 Unleash (Feature Toggles) 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": {
    "unleash-feature-toggles-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 Unleash. 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 Unleash (Feature Toggles) 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 Unleash (Feature Toggles) MCP in Claude Code

It lets your scripts check feature flags against the target environment before deploying. This means you won't deploy code that relies on a toggle that hasn't been activated yet.

Absolutely. Use `list_projects` to get every project ID, then run `list_environments` to see which deployment stages are configured for the release pipeline.

You can use `get_frontend_features`, passing the necessary context like a segment ID or project ID. This ensures your automated tests run against the correct set of toggles.

Run `list_users` to pull a comprehensive list of every configured account. This is critical before running automated security scans or access checks.

This server handles and reports on user identification via the `list_users` tool, which accesses user accounts for auditing purposes.

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