Skip to main content

LAX MCP Flow Generation Cursor Client Server

Project description

LambdaX MCP Flow Generation Cursor Client

This is a client-side MCP server that acts as a proxy to the backend LAX MCP Flow Generation server. It solves the performance issue of sending large JSON files through the MCP protocol by handling file reading locally and forwarding requests to the backend server.

Architecture

Cursor → Cursor Client MCP Server → Backend MCP Server
  • Cursor: The IDE client that connects to our local MCP server
  • Cursor Client MCP Server: This server (stdio transport) that handles file I/O and forwards requests
  • Backend MCP Server: The original LAX MCP Flow Generation server (HTTP transport)

Features

  • File Path Support: Tools can accept file paths instead of requiring full JSON objects
  • Automatic File Reading: Reads JSON files locally to avoid large data transfers
  • Transparent Forwarding: All requests are forwarded to the backend server
  • Same Interface: Exposes identical tools as the original server
  • Error Handling: Proper error handling for file operations and network requests

Available Tools

  • validate_flow: Validates flow JSON (supports file paths)
  • search_flows: Search for similar flows
  • search_flows_by_node: Search flows by specific node
  • search_nodes: Search for available nodes
  • check_flow_exists_lax: Check if flow exists in LAX
  • search_advanced_features: Search for advanced features
  • search_functions: Search for transform functions
  • fetch_execution_of_node: Get node execution examples
  • get_node_by_name: Get node details by name
  • think: Log reasoning and analysis
  • get_flow_by_name: Retrieve flow by name
  • save_flow_to_lax: Save flow to LambdaX (supports file paths)

Usage

Add this to your Cursor MCP configuration:

{
    "mcpServers": {
      "lax-mcp-flow-generation": {
        "command": "lax-mcp-flow-gen",
        "args": [],
        "env": {
           "BACKEND_SERVER_URL": "http://localhost:8000/mcp?username=YOUR_USERNAME&password=YOUR_PASSWORD"
        }
      }
    }
  }

Examples

Using validate_flow with file path

Instead of:

{
  "flow_json": { /* large JSON object */ }
}

You can now use:

{
  "flow_json": "/path/to/flow.json"
}

The server will automatically read the file and forward the content to the backend.

Environment Variables

  • BACKEND_SERVER_URL: URL of the backend MCP server (default: http://localhost:8000/mcp)
  • LOG_LEVEL: Logging level (default: INFO)
  • MAX_FILE_SIZE: Maximum file size in bytes (default: 10485760 = 10MB)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lax_mcp_flow_generation_cursor_client-0.0.2.tar.gz (11.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file lax_mcp_flow_generation_cursor_client-0.0.2.tar.gz.

File metadata

File hashes

Hashes for lax_mcp_flow_generation_cursor_client-0.0.2.tar.gz
Algorithm Hash digest
SHA256 bd84c0c81e04e831d7375f10351cee0366f756d39a274d6654bfffac69249188
MD5 47fabe2c45bac31f9c0eca58fa5a4254
BLAKE2b-256 7186765b92ae04c7fcf14057c99918f836ed88cd9456f24f4a352588c5d66980

See more details on using hashes here.

File details

Details for the file lax_mcp_flow_generation_cursor_client-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for lax_mcp_flow_generation_cursor_client-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 911f71a85b0ae2c6a6f35126f15698269df1eb734f278babe156f7d4e7646ac1
MD5 d1a117c298e60fce73eba8d504dd1aa2
BLAKE2b-256 5e3d0e5e76049ff06aa9edab9c31b5981708817519c7215dd51b0fe95823af26

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page