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

Q: How does LlamaIndex index data from Lindy (Autonomous AI Employees)?

You run a query pipeline that calls listruns and getrunlogs to fetch execution data. LlamaIndex then parses these logs and stores them as document nodes in your vector database.

Q: Can my LlamaIndex agent trigger new runs?

Yes, your agent can call triggerlindy using our MCP client with a JSON payload constructed from user queries. This lets LlamaIndex move from answering questions to executing real-world tasks.

Q: Can I search across multiple workspaces?

Call listworkspaces to retrieve all team boundaries. Your LlamaIndex application can then partition its vector index so search results stay restricted to the correct team.

Index Lindy execution logs and workspace data directly into LlamaIndex vector stores.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index autonomous agent history in LlamaIndex

Feed your RAG pipelines with actual execution data. Use `list_runs` and `get_run_logs` to ingest raw agent reasoning paths directly into your LlamaIndex vector store using this MCP integration. This turns past execution logs into searchable knowledge. Your LlamaIndex query engine can search past runs to answer questions about what your agents did last week.

Query workspace configurations via MCP Server

Let your LlamaIndex agent query your active workspace setup. By calling `list_workspaces` and `list_lindies`, your RAG application grounds its answers in actual workspace structures. Pull specific agent configurations using `get_lindy`. This gives your index access to the exact prompts and tool mappings running in your active workspace.

Map active integrations for semantic search

Use `list_integrations` to fetch all connected third-party apps like Slack or Gmail. LlamaIndex indexes this metadata so your agent knows exactly which data sources are live. When a user asks what tools are available, LlamaIndex queries this index instead of making blind API calls. It keeps your RAG applications fast and accurate.

Setup guide

Set up Lindy (Autonomous AI Employees) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Lindy (Autonomous AI Employees) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Lindy (Autonomous AI Employees) tools.",
)
response = await agent.run("List recent Lindy (Autonomous AI Employees) data")

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 LlamaIndex

You run a query pipeline that calls `list_runs` and `get_run_logs` to fetch execution data. LlamaIndex then parses these logs and stores them as document nodes in your vector database.

Yes, your agent can call `trigger_lindy` using our MCP client with a JSON payload constructed from user queries. This lets LlamaIndex move from answering questions to executing real-world tasks.

If your LlamaIndex agent detects an execution anomaly while polling `get_run`, it can call `cancel_run` to stop the loop. This prevents your index from getting flooded with corrupted run data.

Call `list_workspaces` to retrieve all team boundaries. Your LlamaIndex application can then partition its vector index so search results stay restricted to the correct team.

Yes, because the MCP Server processes configuration details like `list_triggers` locally in a secure sandbox. Your LlamaIndex pipeline only indexes the text metadata, never your raw API keys or database credentials.

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