How to Use the LaunchDarkly MCP in AutoGen

Q: How do I register the LaunchDarkly MCP Server tools with my AutoGen agents?

Use mcpservertools from the autogen-extmcp package to load the server tools. Pass the resulting tool list directly to your AssistantAgent constructors. This allows your agents to invoke tools like listfeatureflags during their chats.

Q: Can AutoGen agents automatically detect drift in LaunchDarkly environments?

Yes, they can. A dedicated monitoring agent can call listenvironments and share the output with a supervisor agent. Together, they compare configurations across environments to identify and flag any unauthorized drift.

Q: How do AutoGen agents collaborate to review LaunchDarkly audit logs?

One agent retrieves the audit trail using listauditlogs, and another parses it to identify recent changes. They cross-reference these events against listprojects to determine which project was modified and whether the change was authorized.

Q: What transport protocols does this integration support?

It supports both stdio and streamable HTTP transports. The McpToolAdapter in AutoGen handles the schema conversion automatically, ensuring smooth communication with the Vinkius hosted endpoint.

Deploy collaborative AutoGen agents to debate, audit, and verify your LaunchDarkly flag configurations before releases.

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 AutoGen

Create your Vinkius account to connect LaunchDarkly to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate flag safety with AutoGen agents

The `get_feature_flag` tool provides deep configuration details to your specialized AutoGen agents during their collaborative debate. One agent can play the role of a security auditor, while another acts as a release manager. They evaluate the active targeting rules side-by-side. By discussing the JSON payload returned from the tool, the agents reach a consensus on whether the flag configuration complies with your team's release policies.

Coordinate multi-environment audits via MCP Server

The `list_environments` tool retrieves all environmental targets for your multi-agent conversation. This allows your testing agent to verify staging setups while your deployment agent checks production parameters. The agents exchange environmental data to verify parity. If they detect a discrepancy, they query `get_environment` to resolve the conflict and log the decision in their chat history.

Verify experimentation metrics before rollouts

The `get_metric` tool pulls specific performance metrics to let your analytical agents evaluate the success of an active experiment. They inspect the metric definitions to ensure your telemetry aligns with expected business outcomes. This data is cross-referenced with `list_metrics` to give your agents a complete view of active experiments. They debate the results and decide if a feature is ready for a full rollout or needs to be rolled back.

Setup guide

Set up LaunchDarkly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes LaunchDarkly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="LaunchDarkly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LaunchDarkly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="LaunchDarkly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LaunchDarkly data")
    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 AutoGen

Use `mcp_server_tools` from the `autogen-ext[mcp]` package to load the server tools. Pass the resulting tool list directly to your `AssistantAgent` constructors. This allows your agents to invoke tools like `list_feature_flags` during their chats.

Yes, they can. A dedicated monitoring agent can call `list_environments` and share the output with a supervisor agent. Together, they compare configurations across environments to identify and flag any unauthorized drift.

One agent retrieves the audit trail using `list_audit_logs`, and another parses it to identify recent changes. They cross-reference these events against `list_projects` to determine which project was modified and whether the change was authorized.

It supports both stdio and streamable HTTP transports. The `McpToolAdapter` in AutoGen handles the schema conversion automatically, ensuring smooth communication with the Vinkius hosted endpoint.

Vinkius processes all requests inside isolated, ephemeral V8 sandboxes. Your audit logs, environment keys, and feature flag configurations are never cached, logged, or written to disk. The connection token is encrypted, ensuring zero-trust security for your live production data.

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