- Home
- MCP servers
- Langflow
Langflow
- typescript
3
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You deploy and run an MCP server that bridges Langflow with AI assistants, enabling flows to be created, executed, and managed through conversational tooling. It provides structured access to Langflow features and lets you control flows, builds, imports/exports, knowledge bases, components, and monitoring from your MCP-enabled client.
How to use
You use this MCP server from an MCP client (such as Claude Desktop) to manage Langflow flows and run automations. Connect in stdio mode for local desktop clients or in http mode for remote access. In stdio mode, start the MCP server locally and point your client at the local process. In http mode, expose the MCP server on a port and secure it with a token to allow your client to communicate over HTTP.
How to install
# Prerequisites
- Node.js installed on your system
- A running Langflow instance
- Langflow API key
# Install from npm (global)
npm install -g langflow-mcp-server
# OR clone the repository
git clone https://github.com/nobrainer-tech/langflow-mcp.git
cd langflow-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Configure environment
cp .env.example .env
# Edit .env with your Langflow instance URL and API key
Configuration and usage notes
Prepare a local environment file to configure the server. The key settings include the Langflow base URL, API key, and the MCP mode. You can run in stdio mode for direct client integration or http mode for remote access.
LANGFLOW_BASE_URL=http://localhost:7860
LANGFLOW_API_KEY=your-api-key-here
MCP_MODE=stdio
LOG_LEVEL=info
Claude Desktop setup (stdio mode)
Add a configuration for Langflow MCP within Claude Desktop so you can issue MCP commands directly from Claude.
{
"mcpServers": {
"langflow": {
"command": "npx",
"args": ["-y", "langflow-mcp-server"],
"env": {
"LANGFLOW_BASE_URL": "http://localhost:7860",
"LANGFLOW_API_KEY": "your-api-key-here",
"MCP_MODE": "stdio",
"LOG_LEVEL": "error"
}
}
}
}
Alternative local installation command (stdio mode)
If you prefer running directly from a built distribution, place the MCP server start command in Claude Desktop as shown.
{
"mcpServers": {
"langflow": {
"command": "node",
"args": ["/absolute/path/to/langflow-mcp/dist/mcp/index.js"],
"env": {
"LANGFLOW_BASE_URL": "http://localhost:7860",
"LANGFLOW_API_KEY": "your-api-key-here",
"MCP_MODE": "stdio",
"LOG_LEVEL": "error"
}
}
}
}
Docker deployment and quick start
You can run the MCP server in Docker for isolation and reproducibility. Use docker-compose for a quick start or build and run a standalone image for more control.
# Quick start with Docker (clone and docker-compose)
git clone https://github.com/nobrainer-tech/langflow-mcp.git
cd langflow-mcp
docker-compose up -d
docker-compose logs -f
docker-compose down
Building and running a Docker image
Build a standalone image and run in stdio mode locally or in http mode for remote access.
# Build the image
docker build -t langflow-mcp-server:latest .
# Run in stdio mode (for Claude Desktop)
docker run -it --rm \
-e LANGFLOW_BASE_URL=http://localhost:7860 \
-e LANGFLOW_API_KEY=your-api-key \
langflow-mcp-server:latest
# Run in HTTP mode (for remote access)
docker run -d \
-p 3000:3000 \
-e MCP_MODE=http \
-e PORT=3000 \
-e AUTH_TOKEN=your-secure-token \
-e LANGFLOW_BASE_URL=http://langflow:7860 \
-e LANGFLOW_API_KEY=your-api-key \
langflow-mcp-server:latest
Docker Compose configuration
The provided docker-compose setup supports both stdio and HTTP modes. Use the environment section to switch modes and set the base URL and API key.
# STDIO mode (default)
environment:
- MCP_MODE=stdio
- LANGFLOW_BASE_URL=http://localhost:7860
- LANGFLOW_API_KEY=your-key
# HTTP mode
environment:
- MCP_MODE=http
- PORT=3000
- AUTH_TOKEN=your-secure-token
Security and deprecated tools notes
If your setup exposes the MCP over HTTP, protect it with a strong token and restrict access to trusted clients.
The server includes deprecated tool endpoints by default. You can disable deprecated tools by setting ENABLE_DEPRECATED_TOOLS to false in your environment.
Troubleshooting and tips
Ensure your Langflow instance is reachable at the configured base URL and that the API key is valid. Check logs for connection errors and verify that the MCP_MODE matches your client (stdio for local desktop usage, http for remote access). If you change configuration, restart the MCP server to pick up new settings.
Available tools
create_flow
Create a new Langflow flow
list_flows
List all flows with pagination and filtering
get_flow
Get details of a specific flow by ID
update_flow
Update an existing flow
delete_flow
Delete a single flow
delete_flows
Delete multiple flows at once
run_flow
Execute a flow with input configuration (supports streaming)
trigger_webhook
Trigger a flow via webhook endpoint
upload_flow
Upload a flow from JSON data
download_flows
Download multiple flows as JSON export
get_basic_examples
Get pre-built example flows
list_folders
List all folders with pagination
create_folder
Create a new folder
get_folder
Get folder details by ID
update_folder
Update folder name, description, or parent
delete_folder
Delete a folder
list_projects
List all projects with pagination
create_project
Create a new project
get_project
Get project details by ID
update_project
Update project name or description
delete_project
Delete a project
upload_project
Upload a project from JSON data
download_project
Download a project as JSON export
list_variables
List all global variables
create_variable
Create a new variable
update_variable
Update variable properties
delete_variable
Delete a variable
build_flow
Build/compile a flow and return job_id for async execution
get_build_status
Poll build status and events for a specific job
cancel_build
Cancel a running build job
list_knowledge_bases
List all available knowledge bases
get_knowledge_base
Get detailed information about a specific knowledge base
delete_knowledge_base
Delete a specific knowledge base
bulk_delete_knowledge_bases
Delete multiple knowledge bases at once
list_components
List all available Langflow components
upload_file
Upload a file to a specific flow
download_file
Download a file from a flow
list_files
List all files in a flow
delete_file
Delete a file from a flow
get_file_image
Get an image file from a flow
get_monitor_builds
Get build execution history for a flow
get_monitor_messages
Query chat/message history with filtering
get_monitor_message
Get details of a specific message
get_monitor_sessions
List all chat session IDs
get_monitor_session_messages
Get all messages for a session
migrate_monitor_session
Migrate messages between sessions
get_monitor_transactions
List transaction logs for a flow
delete_monitor_builds
Delete build history for a flow
delete_monitor_messages
Delete multiple messages by ID
build_vertices
(DEPRECATED) Get vertex build order for a flow
get_vertex
(DEPRECATED) Get details of a specific vertex/component
stream_vertex_build
(DEPRECATED) Stream real-time build events for a vertex
list_users
List all users (admin only)
get_current_user
Get current authenticated user info
get_user
Get details of a specific user
update_user
Update user profile information
reset_user_password
Reset password for a user (admin only)
list_api_keys
List all API keys for the user
create_api_key
Create a new API key
delete_api_key
Delete an API key
list_custom_components
List all custom components
create_custom_component
Create a new custom component
login
Authenticate with username and password
auto_login
Auto-login with stored credentials
refresh_token
Refresh authentication token
logout
Logout and invalidate session
check_store
Check if component store is enabled
check_store_api_key
Validate a store API key
list_store_components
Browse available components in the store
get_store_component
Get details of a store component
list_store_tags
List all component tags in the store
get_user_likes
Get components liked by user
validate_code
Validate Python code for custom components
validate_prompt
Validate prompt template syntax
run_flow_advanced
Advanced flow execution with full control
process_flow
Legacy process endpoint for flows
predict_flow
Legacy predict endpoint for flows
get_public_flow
Get a public flow without authentication
batch_create_flows
Create multiple flows in one operation