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

Q: How do I trigger Lindy (Autonomous AI Employees) runs inside a LangChain chain?

You use the triggerlindy tool directly inside your chain or LangGraph node. Pass the required JSON payload from the previous chain output, and LangChain will initiate the asynchronous run.

Q: Can LangChain handle human-in-the-loop pauses with this MCP Server?

Yes. Your LangChain agent can poll getrun to check if a Lindy run is blocked on human approval. Once approved, the chain continues executing its next steps.

Q: How do I debug failing Lindy (Autonomous AI Employees) steps in LangChain?

Use getrunlogs to dump the raw reasoning logs directly into your LangSmith tracing dashboard. You'll see the exact step where the autonomous run failed or got stuck.

Q: Can I list available agents dynamically in my LangChain setup?

Call listlindies to fetch all configured agents in your workspace. Your LangChain router can then inspect their prompts and tools via getlindy to decide which one to run.

Run and audit your Lindy autonomous agents 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 Lindy (Autonomous AI Employees) MCP to LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Lindy executions in LangChain

Kick off autonomous agents using `trigger_lindy` as a step in your chain. LangChain passes the output of one step directly into the next, letting you build multi-step reasoning runs without manual glue code. If a run gets stuck, your chain can hit `cancel_run` to stop execution before you rack up a massive API bill. This keeps your agentic loops fast and predictable.

Debug agent loops with LangChain and MCP Server

Stop guessing what your autonomous agents are doing. Pull raw LLM reasoning logs using `get_run_logs` and feed them directly into LangSmith for tracing and debugging. You get deep visibility into execution graphs. Track exactly when a run pauses for human input or hits external APIs by polling `get_run` inside your LangChain agent loop.

Map workspaces and integrations dynamically

Before triggering a task, have your LangChain agent call `list_workspaces` and `list_integrations` to check where the data needs to go. Your agent inspects the environment first to make sure it has the right context. Use `list_lindies` to let your chain select the exact configured agent for the job. No hardcoded IDs, just dynamic routing based on the task at hand.

Setup guide

Set up Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) 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({
    "lindy-autonomous-ai-employees-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 Lindy (Autonomous AI Employees) 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 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 LangChain

You use the `trigger_lindy` tool directly inside your chain or LangGraph node. Pass the required JSON payload from the previous chain output, and LangChain will initiate the asynchronous run.

Yes. Your LangChain agent can poll `get_run` to check if a Lindy run is blocked on human approval. Once approved, the chain continues executing its next steps.

Use `get_run_logs` to dump the raw reasoning logs directly into your LangSmith tracing dashboard. You'll see the exact step where the autonomous run failed or got stuck.

Call `list_lindies` to fetch all configured agents in your workspace. Your LangChain router can then inspect their prompts and tools via `get_lindy` to decide which one to run.

Vinkius runs the MCP Server in an isolated sandbox, meaning your Slack and Gmail tokens from `list_integrations` are never exposed to the LLM or LangChain. Only the execution status and logs pass through.

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