How to Use the LaunchDarkly MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent view LaunchDarkly metrics?

Yes. Your agent uses getmetric to pull performance data. It helps your code make logic decisions based on real-time experimentation results.

Q: How does this MCP Server handle LaunchDarkly project lists?

It uses listprojects to fetch your account's project catalog. Your agent then selects the correct project key to scope all further flag queries.

Control your feature flags directly from your OpenAI Agents SDK workflow without switching context or manually checking the dashboard.

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 OpenAI Agents SDK

Create your Vinkius account to connect LaunchDarkly to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query LaunchDarkly flags in OpenAI Agents SDK

Your agent inspects flag states using `get_feature_flag` to make informed decisions during runtime. It pulls live configuration data so your logic stays synced with what's actually deployed. Stop guessing if a feature is active. By calling `list_feature_flags`, your agent gets a clear picture of all available toggles, ensuring your deployment scripts operate on current data.

Audit deployment history via MCP Server

Trace recent modifications by firing `list_audit_logs` within your agent flow. You get a direct look at who changed a flag and when, right inside your logs. This MCP Server provides the raw audit trail your agent needs to verify stability. It turns opaque configuration changes into actionable data points for your automated monitoring systems.

Manage environment context for your agent

Use `list_environments` to verify which target environment your agent is currently hitting. It prevents accidental configuration changes in production by confirming the environment ID first. Your agent checks specific environment details with `get_environment` before taking action. It adds a layer of awareness to your automated pipeline, making sure every command hits the right target.

Setup guide

Set up LaunchDarkly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LaunchDarkly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LaunchDarkly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LaunchDarkly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LaunchDarkly Agent",
            instructions="You have access to LaunchDarkly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the server and pass it to your Agent constructor using mcp_servers. The tools will auto-discover, letting your agent call LaunchDarkly functions directly.

Yes. Your agent uses `get_metric` to pull performance data. It helps your code make logic decisions based on real-time experimentation results.

Your agent handles data locally within your defined guardrails. The MCP Server only returns the specific flag or project data you request, keeping your environment isolated.

It uses `list_projects` to fetch your account's project catalog. Your agent then selects the correct project key to scope all further flag queries.

It reads feature flag configurations, audit logs, and environment metadata. No user PII or sensitive keys are stored by the server itself, as it only mirrors your existing project state.

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