mcpField
M
mcp-rs485

mcp-rs485

Local
github.com/daedalusOther0Updated 27w ago
Repository

About mcp-rs485

mcp-rs485 is an MCP server for AI assistants interacting with RS485 devices. It exposes serial-port discovery, connection management, and read/write operations with configurable serial parameters.

Key features

  1. 01List available serial ports
  2. 02Open and close RS485 connections
  3. 03Read and write hexadecimal data
  4. 04Check connection status and statistics
  5. 05Configure serial communication parameters

Use cases

  1. 01Discover serial ports on a system
  2. 02Send commands to an RS485 device
  3. 03Read data from an open RS485 connection

MCP support

It exposes RS485 connectivity to MCP clients through tools for listing ports, managing connections, reading and writing data, and checking connection status.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "daedalus-mcp-rs485": {
      "command": "uvx",
      "args": [
        "mcp-rs485"
      ]
    }
  }
}
Run commanduvx mcp-rs485

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-rs4850.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-rs485

MCP server that exposes RS485 bus connectivity for reading and writing serial data.

mcp-name: io.github.daedalus/mcp-rs485

PyPI Python Ruff

Install

pip install mcp-rs485

Configuration

{
  "mcpServers": {
    "mcp-rs485": {
      "command": "mcp-rs485",
      "env": {},
      "name": "io.github.daedalus/mcp-rs485"
    }
  }
}

Usage

This MCP server exposes RS485 serial bus connectivity through the Model Context Protocol. It allows AI assistants to interact with RS485 devices.

Tools
  • list_ports: Lists all available serial ports on the system
  • connect_rs485: Opens a connection to an RS485 device
  • disconnect_rs485: Closes an RS485 connection
  • read_rs485: Reads data from an open RS485 connection
  • write_rs485: Writes data to an RS485 connection
  • get_connection_status: Gets the status of an RS485 connection
Example
from mcp_rs485.server import connect_rs485, write_rs485, read_rs485

# Connect to a device
conn_id = connect_rs485("/dev/ttyUSB0", baudrate=9600)

# Write data (Modbus RTU example)
write_rs485(conn_id, "01 03 00 00 00 0A")

# Read response
response = read_rs485(conn_id)

# Cleanup
disconnect_rs485(conn_id)

Development

git clone https://github.com/daedalus/mcp-rs485.git
cd mcp-rs485
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

API

list_ports()

Lists all available serial ports.

Returns: List of port dictionaries with port, description, and hwid.

connect_rs485(port, baudrate=9600, parity="N", stopbits=1, bytesize=8, timeout=1.0)

Opens a connection to an RS485 device.

Parameters:

  • port: Serial port path (e.g., "/dev/ttyUSB0")
  • baudrate: Communication speed (default: 9600)
  • parity: "N" (none), "E" (even), "O" (odd)
  • stopbits: Number of stop bits
  • bytesize: Data bits per frame
  • timeout: Read timeout in seconds

Returns: Connection ID string.

read_rs485(connection_id, length=1024)

Reads data from an open RS485 connection.

Parameters:

  • connection_id: Connection ID from connect_rs485
  • length: Maximum bytes to read

Returns: Hex string of received data.

write_rs485(connection_id, data)

Writes data to an RS485 connection.

Parameters:

  • connection_id: Connection ID from connect_rs485
  • data: Hex string (e.g., "01 03 00 00 00 0A")

Returns: Number of bytes written.

get_connection_status(connection_id)

Gets connection status and statistics.

Returns: Dictionary with connection state and statistics.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.