An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Lindy Autonomous AI Employees to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run and audit autonomous agents through your favorite AI client.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Lindy.

  1. 01

    Get lindy

    This capability retrieves the specific configuration, prompt instructions, and capability mappings for a single Lindy.

  2. 02

    Get run

    Use this to check the current status of a run that is currently waiting on a human or an external API.

  3. 03

    List integrations

    This capability provides a secure list of all third-party app connections, like Gmail or Slack, that your Lindies use.

  4. 04

    List lindies

    This capability returns a full list of all custom autonomous assistants built within your workspace.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Lindy.

  1. 05

    List triggers

    Use this to see how your agents are being activated, whether through webhooks, cron jobs, or APIs.

  2. 06

    List workspaces

    This capability lists the organizational boundaries and teams that structure your Lindy deployments.

  3. 07

    Trigger lindy

    This capability starts a new asynchronous task run for a Lindy by passing it a dynamic JSON payload.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Lindy.

  1. 08

    Cancel run

    Use this to send a hard stop to a running execution, which is useful for breaking out of context loops.

  2. 09

    Get run logs

    This capability pulls the raw LLM reasoning logs for a specific run loop so you can audit agent logic.

  3. 10

    List runs

    This capability shows your recent execution history and identifies which Lindy instances are currently active.

Real work

What teams actually run

01

Debugging Agent Logic

A developer pulls reasoning logs to find out why a Lindy failed to complete a specific step in a workflow.

02

Workflow Triggering

An operations manager starts a new research task by sending a JSON payload to a Lindy via their AI client.

03

Process Monitoring

A team lead checks the status of active runs to ensure automated customer support tasks are moving forward.

04

Security Auditing

A founder reviews the list of third-party app integrations to see what data the AI workforce can access.

Automate a task

Put Lindy to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Lindy works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Lindy to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

919ms average. Fast in production.

Lindy is checked daily against the live service.

Daily averagePeak 1079ms
Oct 3Today
Fastest day
711ms
Slowest day
1079ms
14-day trend
Stable0%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Lindy, so you can see the experience inside your AI.

It does not authenticate your account with Lindy. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Lindy Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_c2F5Hk7TPFg1Cz9vjMKKvEPPvQH0HYkK2vL7pHhF/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Lindy capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "lindy-autonomous-ai-employees-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_c2F5Hk7TPFg1Cz9vjMKKvEPPvQH0HYkK2vL7pHhF/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Lindy in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Lindy owners hand off.

This MCP is built for people managing automated business processes who need direct oversight of AI agents.

  • 01

    Operations Managers

    They trigger specialized Lindies to handle repetitive tasks and monitor their progress.

  • 02

    Developers

    They use the reasoning logs to debug agent logic without needing to run manual API tests.

  • 03

    Founders

    They audit how AI integrations are performing across different teams and organizational boundaries.

FAQ

Questions Lindy owners ask.

  • 01

    How do I connect my Lindy account?

    You just need to subscribe to the MCP on Vinkius and enter your Lindy API Token. Once that is done, you can use it immediately in any compatible client.

  • 02

    Can I stop a Lindy if it gets stuck?

    Yes. You can use the cancel run capability to send a hard stop to an execution, which is specifically designed to interrupt agents stuck in context loops.

  • 03

    What clients can I use with this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 04

    How do I see why an agent made a certain decision?

    You can use the get run logs capability to dump the literal LLM reasoning logs for a specific run, allowing you to see the agent's step-by-step logic.

  • 05

    Does this work with my existing Slack or Gmail integrations?

    Yes. You can use the list integrations capability to see and manage the secure connections your Lindies have with third-party apps.

  • 06

    Can I see exactly how my Lindy made a specific decision?

    Yes. Use the get_run_logs capability with a specific Run ID. Your agent will retrieve the literal LLM reasoning loops and step-by-step validations, giving you full transparency into the autonomous agent's logic.

  • 07

    How do I trigger an autonomous task through a conversation?

    The trigger_lindy capability allows you to start an asynchronous task run. You just need to provide the Lindy ID and a JSON payload defining the inputs for the task. Your agent will fire the job and return a Run ID for status tracking.

  • 08

    Can my agent list which third-party apps my Lindies are connected to?

    Absolutely. Use the list_integrations capability to retrieve all active third-party app connections. Your agent will report which channels (like Slack, Gmail, or HubSpot) are securely connected to your workspace.

Explore

More in Superpower

Suggestions

Connect Lindy to Claude, Cursor, ChatGPT & more