How to Use the Lindy (Autonomous AI Employees) MCP in AutoGen

Q: Can a critic agent analyze logs from this MCP Server?

Yes, your critic agent can call getrunlogs to retrieve the step-by-step reasoning of a run. It then reviews the output and suggests corrections to the group.

Q: How do AutoGen agents handle blocked runs in Lindy (Autonomous AI Employees)?

Agents poll getrun to check the execution state. If the run is blocked on human input, the AutoGen coordinator can ping the user in the chat to unblock it.

Q: Can my agents see what integrations are connected?

Use listintegrations to let your agents inspect live third-party connections. This prevents agents from attempting tasks that require disconnected tools.

Q: Where are my workspace logs stored during AutoGen runs with Lindy (Autonomous AI Employees)?

The MCP Server fetches logs on-demand via getrunlogs through a secure connection. Vinkius executes this in an ephemeral sandbox, meaning your execution logs are never saved or cached on our servers.

Let your AutoGen agents debate, trigger, and audit Lindy autonomous runs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lindy (Autonomous AI Employees) MCP to AutoGen

Create your Vinkius account to connect Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven agent execution in AutoGen

Let your AutoGen agents debate whether to start a task via our MCP Server. Once they agree, one agent calls `trigger_lindy` to run the task asynchronously while the others monitor the state. If a run starts looping or failing, a monitoring agent can call `cancel_run` to kill the execution. This setup keeps your autonomous workflows safe and cost-effective.

Audit reasoning logs via MCP Server

AutoGen agents can inspect each other's work. Use `get_run_logs` to dump raw LLM reasoning logs, letting a critic agent analyze the decision-making process of a run. This creates a tight feedback loop. Agents can read the logs, find errors, and adjust the next payload before triggering another run.

Discover triggers and configurations dynamically

Let your coordinator agent call `list_triggers` and `list_lindies` to map out what configurations are live. The agent uses this map to assign tasks to the right Lindy. Pull specific tool mappings with `get_lindy` so your AutoGen group understands exactly what capabilities each autonomous employee has before delegating work. Your agents won't waste time querying incompatible services.

Setup guide

Set up Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) 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="Lindy (Autonomous AI Employees)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Lindy (Autonomous AI Employees) 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="Lindy (Autonomous AI Employees)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Lindy (Autonomous AI Employees) 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 Lindy. 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 Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) MCP in AutoGen

One agent is assigned the tool executor role. After the group chats and agrees on the payload, this agent calls `trigger_lindy` to kick off the background task.

Yes, your critic agent can call `get_run_logs` to retrieve the step-by-step reasoning of a run. It then reviews the output and suggests corrections to the group.

Agents poll `get_run` to check the execution state. If the run is blocked on human input, the AutoGen coordinator can ping the user in the chat to unblock it.

Use `list_integrations` to let your agents inspect live third-party connections. This prevents agents from attempting tasks that require disconnected tools.

The MCP Server fetches logs on-demand via `get_run_logs` through a secure connection. Vinkius executes this in an ephemeral sandbox, meaning your execution logs are never saved or cached on our servers.

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