Langflow (Visual Multi-agent Orchestrator)

Langflow (Visual Multi-agent Orchestrator) MCP Connector for Claude

A+

Orchestrate multi-agent AI workflows visually — execute flows, manage projects, and trigger webhooks directly from any AI agent.

24 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Connect your Langflow instance to any AI agent and take full control of your multi-agent orchestration through natural conversation.

What you can do

  • Flow Execution — Run specific flows by ID or name using run_flow, supporting both chat and text input types.
  • Workflow Management — Execute complex background jobs with run_workflow or use the OpenAI-compatible create_response endpoint.
  • Project Organization — List, create, and manage projects (folders) to keep your agentic workflows structured via list_projects.
  • Flow Lifecycle — Query, update, or delete existing flows directly from your conversation to iterate on agent logic in real-time.
  • External Triggers — Start flow runs in response to external events using the trigger_webhook tool.

How it works

  1. Subscribe to this server
  2. Enter your Langflow Base URL and API Key
  3. Start orchestrating complex AI agents from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — rapidly test and trigger complex RAG or multi-agent flows without leaving the terminal or code editor.
  • Product Teams — monitor and manage flow versions and project folders through simple natural language queries.
  • DevOps & Automation Leads — integrate visual AI logic into broader systems by triggering webhooks and background workflows.
multi-agentai-orchestrationvisual-programminglangflowworkflow-automation

24 tools expose this connector's capabilities to your AI agent.

create_response

Uses flow_id as the model. OpenAI compatible responses endpoint

get_monitor_transactions

Use this to track system component interactions. Retrieve component interaction logs

delete_file_v2

Pass the File ID of the file to be deleted. Delete a file (v2)

delete_flow

Specify the Flow ID of the flow you intend to delete. Delete a flow

get_logs

Retrieve recent logs

get_monitor_messages

Retrieve chat history

list_files_v2

List user files (v2)

list_flows

List all flows

list_projects

List all projects

run_flow

Supports chat or text inputs. Execute a Langflow flow

run_workflow

Run a workflow (v2 API)

trigger_webhook

Trigger a Langflow webhook

whoami

This tool requires no parameters. Get current authenticated user info

create_flow

Provide the complete flow configuration JSON in the flow_data parameter. Create a new flow

create_project

Pass the required project configuration JSON in the project_data parameter. Create a new project

delete_project

Specify the Project ID of the project to be deleted. Delete a project

get_file_v2

Provide the File ID in the file_id parameter. Download a file (v2)

get_flow

Pass the required Flow ID in the id parameter. Get a specific flow by ID

get_monitor_traces

Retrieve execution traces and span trees

get_project

Use the Project ID to identify the desired project. Get project details

list_files_v1

Provide the Flow ID in the flow_id parameter. List files for a specific flow (v1)

list_users

Requires superuser privileges to execute. List all users (requires superuser)

update_flow

Supply both the Flow ID and the updated flow configuration JSON. Update an existing flow

update_project

Provide both the Project ID and the updated project information. Update project info

See how to talk to your AI agent using Langflow (Visual Multi-agent Orchestrator).

List all my available flows in Langflow.

I've retrieved your flows. You have 3 active flows: 'Customer Support Agent' (ID: flow-123), 'Data Extraction Pipeline' (ID: flow-456), and 'Market Analyzer' (ID: flow-789).

Run the 'Market Analyzer' flow with the input 'Analyze NVIDIA stock performance'.

Executing 'Market Analyzer'... The flow has completed. The analysis suggests a bullish trend for NVIDIA based on recent quarterly results and AI demand.

Show me all my project folders.

I found 2 projects: 'Production Agents' (ID: proj-001) and 'Experimental Lab' (ID: proj-002).

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

Related Connectors