How to Use the LaunchDarkly MCP in LangChain

Q: How do I connect the LaunchDarkly MCP Server to my LangChain agent?

Install the langchain-mcp-adapters package and initialize the client with your Vinkius server URL. Call client.gettools() and pass them directly to your agent constructor. The adapter translates the schemas automatically so your agent can call tools like listfeatureflags instantly.

Q: What is the best way to handle project selection in LangChain?

Use listprojects to let your agent find the correct project key dynamically. Once the agent identifies the key, it passes that value to subsequent tool calls like listfeatureflags. This eliminates hardcoded values and keeps your chains flexible.

Run multi-step LaunchDarkly flag audits and automated environment checks directly inside your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect LaunchDarkly to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate flag audits with LangChain chains

The `list_feature_flags` tool queries your active flags via the MCP Server to feed raw configuration data directly into your agent's current prompt context. Your agent inspects targeting rules and immediately decides whether to pull deeper metrics or flag details. LangChain coordinates this sequence by feeding the output of your flag list directly into the input of `get_feature_flag`. LangSmith logs every step of the execution, tracking latency and exact inputs so you see exactly how the agent evaluated your release state.

Verify deployment states across environments

The `list_environments` tool pulls the status of all environments inside a specific project to let your agent verify release parity. It prevents manual checks by programmatically comparing staging and production configurations side-by-side. If a flag is active in staging but missing in production, the agent catches the drift. It uses `get_environment` to inspect specific environment configurations, ensuring your pipeline flags inconsistencies before they hit your users.

Trace release history with audit logs

The `list_audit_logs` tool exposes the chronological modification history of your LaunchDarkly account directly to your active agent. This allows your agent to correlate sudden system anomalies with specific flag changes or environmental updates. Instead of digging through web consoles, your agent inspects the raw log payloads. It links these changes to your active project lists retrieved via `list_projects` to pinpoint exactly who changed what, and when.

Setup guide

Set up LaunchDarkly MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes LaunchDarkly tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "launchdarkly-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent LaunchDarkly transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the `langchain-mcp-adapters` package and initialize the client with your Vinkius server URL. Call `client.get_tools()` and pass them directly to your agent constructor. The adapter translates the schemas automatically so your agent can call tools like `list_feature_flags` instantly.

Yes, your agent can evaluate flag performance by chaining tools together. It queries active metrics via `list_metrics` and retrieves specific target definitions with `get_feature_flag`. By comparing these datasets, the agent determines if a flag is hitting its performance targets.

It uses ReAct loops to decide which tools to execute based on previous outputs. For instance, the agent can call `list_projects` first, select the correct project, and then automatically invoke `list_environments` to find configuration drifts. Every single tool call is tracked in LangSmith.

Use `list_projects` to let your agent find the correct project key dynamically. Once the agent identifies the key, it passes that value to subsequent tool calls like `list_feature_flags`. This eliminates hardcoded values and keeps your chains flexible.

Vinkius hosts the server in a secure, zero-trust V8 isolate sandbox. Your LaunchDarkly API keys, project configurations, and environment details never persist in the sandbox. All communication occurs over encrypted channels, and the ephemeral container destroys itself immediately after execution.

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