Langflow (Visual Multi-agent Orchestrator) Connector for AI agents.

24 live capabilities

Orchestrate multi-agent workflows and RAG pipelines through natural language.

Live agent request Langflow (Visual Multi-agent Orchestrator) / Connector

Waiting for input…

AI Agent

Why people use Langflow (Visual Multi-agent Orchestrator)

Langflow for Multi-agent Workflow Orchestration

With this Connector, you just talk to your agent. You can ask it to run a flow, tell it to update a project, or pull a trace for a failed run. It keeps you in your flow state by bringing the controls to you.

What Vinkius changes

You get to control your Langflow workflows using only plain English.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

Debugging a RAG pipeline

An engineer asks their agent to check the logs for a specific flow to see why a retrieval failed.
Real-world use case 02

Project Organization

A product lead asks the agent to list all projects to see which flows are currently in production.
Real-world use case 03

Automated Webhooks

A developer sets up a trigger so that a flow runs every time a new lead is added to a CRM.

Complete set · 24capabilities

The complete Langflow (Visual Multi-agent Orchestrator) capability set.

These are the exact actions your AI can choose when you ask it to work with Langflow (Visual Multi-agent Orchestrator).

Capability set01 / 06

01—04

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

01 Capability
Create project
Make a new project folder to organize your work. This keeps your different experiments separated.
02 Capability
Create response
Use a flow_id as the model for an OpenAI-compatible response. This lets you treat a specific flow like a standard model.
03 Capability
Delete file v2
Remove a specific file from your system. Use this to clean up your storage and keep things tidy.
04 Capability
Delete flow
Remove a specific flow from your instance to keep your workspace clean. This helps you prune old tests or retired logic.

Capability set02 / 06

05—08

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

05 Capability
Delete project
Delete a project folder to remove old work. It's a fast way to clear out your project list.
06 Capability
Get file v2
Download a specific file associated with your flows. Use this to grab data or assets directly from the system.
07 Capability
Get flow
Fetch the details of a specific flow using its ID. This is useful for checking configurations without opening the UI.
08 Capability
Get logs
Retrieve recent logs to see how your flows are performing. You can use these to find errors in your agentic chains.

Capability set03 / 06

09—12

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

09 Capability
Get monitor messages
Pull your chat history from the monitor. This lets you see the conversation flow in real time.
10 Capability
Get monitor traces
Get execution traces and span trees for deep debugging. It shows you exactly how different components interacted.
11 Capability
Get monitor transactions
View logs of interactions between different components. It's great for seeing the full lifecycle of a request.
12 Capability
Get project
Fetch the details of a specific project. Use this to see the contents and settings of your project folders.

Capability set04 / 06

13—16

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

13 Capability
List files v1
List all files for a specific flow. This helps you see what assets are tied to a particular workflow.
14 Capability
List files v2
See a list of all user files. Use this to get a high level view of your stored items.
15 Capability
List flows
See a list of every flow you have created. This is the quickest way to see your available workflows.
16 Capability
List projects
View all projects to see your organized workspace. It helps you keep your different workstreams separated.

Capability set05 / 06

17—20

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

17 Capability
List users
See a list of all users on your instance. Use this for administrative oversight of your Langflow environment.
18 Capability
Run flow
Execute a flow using either chat or text inputs. This is the primary way to trigger your visual logic via your agent.
19 Capability
Run workflow
Start a workflow using the v2 API. This is ideal for running more complex, multi-step background jobs.
20 Capability
Trigger webhook
Start a flow run based on an external webhook event. Use this to connect your Langflow flows to other apps.

Capability set06 / 06

21—24

4 capabilities in this set.

Part of 24 available through Langflow (Visual Multi-agent Orchestrator).

21 Capability
Update flow
Modify an existing flow's configuration. You can change logic or settings without having to rebuild the whole thing.
22 Capability
Whoami
See the details of the currently authenticated user. This confirms your identity and permissions within the instance.
23 Capability
Update project
Change the information for a specific project. Use this to rename or re-categorize your project folders.
24 Capability
Create flow
Build a new flow from scratch. Use this to start a new visual agentic workflow immediately.

Set up in minutes

One URL. Then ask Langflow (Visual Multi-agent Orchestrator) to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Langflow (Visual Multi-agent Orchestrator) from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Langflow (Visual Multi-agent Orchestrator), and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Langflow (Visual Multi-agent Orchestrator) for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Langflow (Visual Multi-agent Orchestrator) URL.
Step 03

Save and start

Save the connection and enable Langflow (Visual Multi-agent Orchestrator) in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "langflow-visual-multi-agent-orchestrator": {
      "url": "https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Langflow (Visual Multi-agent Orchestrator)

Open Agent mode in chat and ask: "Using Langflow (Visual Multi-agent Orchestrator), help me...". 24 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "langflow-visual-multi-agent-orchestrator": {
      "url": "https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Langflow (Visual Multi-agent Orchestrator)

Ask Copilot: "Using Langflow (Visual Multi-agent Orchestrator), help me...". 24 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "langflow-visual-multi-agent-orchestrator": {
      "url": "https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Langflow (Visual Multi-agent Orchestrator)

Open Cascade and ask: "Using Langflow (Visual Multi-agent Orchestrator), help me...". 24 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "langflow-visual-multi-agent-orchestrator": {
      "url": "https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Langflow (Visual Multi-agent Orchestrator)

Ask Cline: "Using Langflow (Visual Multi-agent Orchestrator), help me...". 24 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add langflow-visual-multi-agent-orchestrator --transport http "https://edge.vinkius.com/vk_preview_SsoeJOXDcMZ5NDD4MrW7XRXB6MCQXkWhm3WbCM4n/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Langflow (Visual Multi-agent Orchestrator)

Ask Claude: "Using Langflow (Visual Multi-agent Orchestrator), show me...". 24 tools are ready

Where the request belongs

Work Langflow can move forward.

Built around the request

AI engineers who are tired of manual flow triggering and product leads who need to monitor complex agentic pipelines without digging through the Langflow UI.

01

AI Engineer

Runs and debugs RAG pipelines via natural language to speed up testing and iteration.

02

Product Manager

Monitors flow versions and project status to keep stakeholders updated on agent performance.

03

DevOps Engineer

Triggers webhooks and background workflows to integrate AI into production systems.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 7 capabilities

Flowise

Manage low-code AI workflows via Flowise. run predictions, track chatflows and agentflows, handle capabilities, and audit execution history directly from any AI agent.

02 10 capabilities

AutoGen

Orchestrate Microsoft AutoGen multi-agent workflows. manage sessions, agent roles, workflows, and monitor execution logs from any AI agent.

03 10 capabilities

AirOps

AI workflow orchestration. execute models, manage agents, and query memory via AI.

04 10 capabilities

LangGraph Cloud (Stateful AI Agents)

Orchestrate stateful AI agents via LangGraph Cloud. manage assistants, monitor conversation threads, and handle human-in-the-loop overrides.

05 10 capabilities

Lindy (Autonomous AI Employees)

Manage autonomous AI employees via Lindy. trigger task runs, monitor reasoning logs, and audit app integrations.

06 32 capabilities

Activepieces

Automate workflows with Activepieces. manage flows, monitor executions, and handle app connections directly from your AI agent.

Bring your own AI

Change the model, client or framework. Keep Langflow connected.

Before you connect

Questions about Langflow.

The practical details behind the request, access and result.

What is the Langflow MCP for AI Agents?

It lets your AI client interact with your Langflow instance. You can run flows, manage projects, and check logs using just natural language.

Can I use the Langflow MCP to run multi-agent workflows?

Yes. It's designed specifically to let your agent execute complex flows and handle background jobs.

How do I organize my Langflow flows with this?

You can use your agent to create project folders and list them, keeping your agentic workflows structured and easy to find.

Can the Langflow MCP trigger flows from other apps?

Yes. It includes a capability to trigger webhooks, allowing you to start flows based on external events.

Can I debug my Langflow flows using an AI client?

You can. Your agent can retrieve recent logs and execution traces to help you see exactly where a flow might be failing.

Does the Langflow MCP support updating existing flows?

Yes. You can ask your agent to update a flow's configuration or a project's info directly through your conversation.

Can I run a flow using its name instead of a long UUID?

Yes! The run_flow capability accepts either the Flow ID or the Flow Name in the flow_id parameter, making it easy to trigger specific logic by name.

How do I see all the available projects and folders in my Langflow instance?

Use the list_projects capability. It will return a list of all projects (folders) which help organize your flows and components.

Is it possible to trigger a flow from an external webhook payload?

Absolutely. Use the trigger_webhook capability by providing the flow_id and the data JSON payload you want to send to the flow's entry point.

One connection away

Give your agent a direct line to Langflow.

Connect Langflow once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available