How to Use the LaunchDarkly MCP in Mastra AI

Q: How do I register the LaunchDarkly MCP Server in Mastra AI?

Pass the server endpoint to new MCPClient and spread the tools into your Mastra AI agent configuration. The agent instantly gains the ability to query flags using listfeatureflags.

Q: How do I set up human approval for LaunchDarkly changes in Mastra AI?

Use the requireToolApproval config option when setting up your Mastra AI agent. When the agent attempts to inspect audit logs using listauditlogs, the system pauses for developer confirmation first.

Q: Does Mastra AI support multi-project LaunchDarkly setups?

The agent uses listprojects to discover all available projects across your organization. It then targets the correct environment based on your workflow's runtime parameters.

Automate LaunchDarkly rollouts and environment checks inside Mastra AI agent workflows using this MCP Server.

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 Mastra AI

Create your Vinkius account to connect LaunchDarkly to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build reliable LaunchDarkly rollout workflows in Mastra AI.

Running `list_feature_flags` inside a Mastra AI agent lets you monitor feature rollouts and automatically trigger rollback workflows if errors spike. The Mastra AI framework handles the conditional logic, checking if a LaunchDarkly flag is active before executing the next deployment step. If a workflow step fails, the built-in Mastra AI engine retries the `get_feature_flag` call to ensure the flag state is verified. This ensures your automated LaunchDarkly deployment pipeline doesn't break due to temporary network blips.

Run human-in-the-loop audit logs with this MCP Server.

This LaunchDarkly MCP Server provides `list_audit_logs` to let Mastra AI agents monitor configurations and halt pipelines for manual approval when unauthorized changes occur. The Mastra AI framework pauses execution and alerts your team when a production LaunchDarkly flag changes. By calling `list_environments`, the Mastra AI agent verifies which LaunchDarkly environments are affected before notifying the team. This keeps your Mastra AI staging setups moving fast while locking down production LaunchDarkly flag modifications.

Track LaunchDarkly experiment goals inside Mastra AI workflows.

Calling `list_metrics` allows your Mastra AI agent to pull active experiment metrics and automatically decide whether to increase user targeting. The Mastra AI workflow engine evaluates the statistical significance of the data before modifying any LaunchDarkly project state. The Mastra AI agent calls `get_metric` to verify specific LaunchDarkly performance thresholds are met before proceeding. If the LaunchDarkly metrics look bad, the Mastra AI workflow branches to notify your SRE team via Slack.

Setup guide

Set up LaunchDarkly MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All LaunchDarkly tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "launchdarkly-mcp-client",
  servers: {
    "launchdarkly-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "LaunchDarkly Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to LaunchDarkly tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent LaunchDarkly transactions"
);
console.log(result.text);

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 Mastra AI

Pass the server endpoint to `new MCPClient` and spread the tools into your Mastra AI agent configuration. The agent instantly gains the ability to query flags using `list_feature_flags`.

Yes, Mastra AI uses its built-in workflow engine to automatically retry calls like `get_feature_flag` if LaunchDarkly rate limits you. It handles exponential backoff without requiring manual error-handling code.

Use the `requireToolApproval` config option when setting up your Mastra AI agent. When the agent attempts to inspect audit logs using `list_audit_logs`, the system pauses for developer confirmation first.

The agent uses `list_projects` to discover all available projects across your organization. It then targets the correct environment based on your workflow's runtime parameters.

The workflow engine only reads LaunchDarkly project metadata, environment definitions, and flag targeting rules. Vinkius secures these credentials in an ephemeral, zero-trust sandbox, so your production tokens are never exposed to the agent.

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