Modbus TCP/RTU Device

io.github.K-Dense-AIPublished by GitHub account K-Dense-AIv0.1.3Updated Oct 24, 2026

MCP server for Modbus TCP/RTU devices with typed, scaled register maps and per-point limits.

VerifiedSTDIODesktop onlyCloud & InfrastructureDeveloper Tools

Overview

AI-generated overview

A local MCP server that lets an assistant read and control Modbus TCP/RTU devices through a typed, scaled register map with per-point limits.

What you can do
Read named points decoded into engineering units, plus raw holding and input registers, coils and discrete inputs, and inspect the loaded register map and connection info and command log. Write named points such as setpoints, modes and outputs, with values checked against writable flags, min/max or enums before sending and read back afterwards. Write raw registers and coils for addresses the map does not describe. Run a safe-state sequence defined in the map, and reconnect after a power cycle or cable change.
When to use it
Use it when an assistant should monitor or adjust lab and industrial Modbus equipment such as temperature controllers, chillers, PLCs, sensors, VFDs or data loggers, and you can supply a register map for the device. It suits supervised setpoint changes and safe-state recovery more than unattended control.
Requirements
Runs locally as a Python package (uvx labmcp-modbus) over stdio. Needs a register map file (YAML or JSON) and a device address via LABMCP_ADDRESS or the address flag, for example a TCP host and port or a serial port with baud rate and parity. Network or serial access to the device is required; a built-in simulator works without hardware.
Before you install
Write tools act on real equipment: changing setpoints, coils and outputs can start heaters, pumps or motors. Raw write tools bypass scaling and limits, so disabling them once the map is complete is advised. Read-only mode still allows the safe-state tool. Some devices wear out from repeated parameter writes, and a few clear counters or alarms when read. The server is reported as tested only against a simulator, not hardware.

Installation

In SourceWeft

  1. Open Modbus TCP/RTU Device in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Modbus TCP/RTU Device — MCP Server

Let an AI agent read and control Modbus devices over Ethernet (Modbus TCP) or RS-485/RS-232 (Modbus RTU/ASCII): PID temperature controllers, recirculating chillers, PLCs, process sensors, VFDs and data loggers. You describe the device once in a register map (YAML or JSON). The agent then works with named points in real units, such as process_temperature = 37.2 °C or setpoint, instead of raw registers. The server enforces the map's rules: only writable points can be written by name, every writable number must have a min and max, and out-of-range values are refused before anything is sent. The map can also define a safe state, a list of point writes (heater off, controller to standby) that a SAFETY tool runs on request.

Packagelabmcp-modbus
InstrumentsAny Modbus device: temperature controllers (Watlow, Eurotherm, Omega, Autonics, …), chillers and circulators, PLCs and remote I/O, sensors/transmitters, VFDs, power meters, data loggers
InterfacesEthernet (Modbus TCP, port 502), RS-485 / RS-232 (Modbus RTU or ASCII), serial-to-Ethernet gateways (RTU over TCP)
ProtocolMODBUS Application Protocol Specification V1.1b3, MODBUS over Serial Line V1.02, MODBUS Messaging on TCP/IP Implementation Guide V1.0b; client via pymodbus 3.8+
Status🧪 simulated: tested against an in-memory simulated controller and a local pymodbus server, not yet verified on hardware. Report a hardware test

What this server adds over a plain register-poking Modbus MCP:

  • Typed register maps: int16/uint16/int32/uint32/float32/float64/bool, word and byte order, scale and offset, units, enums (0 = standby, 1 = auto) and descriptions.
  • Per-point limits: writable points need min/max or an enum, and values are checked before sending. Raw writes to addresses that belong to a mapped point are refused, so the limits can't be bypassed.
  • Read-back: every write_point reads the value back and reports whether it matches.
  • Safe state: an apply_safe_state SAFETY tool, defined in the map, that works even in --read-only mode.
  • Read-only mode (--read-only), an audit log of every request and reply, and bounded request sizes.

Try it without hardware

bash
uvx labmcp-modbus --simulate --check

The simulator is a generic single-loop PID temperature controller. Its layout is the bundled example register map. It is illustrative and not a copy of any vendor's map. A heater (3 °C/s at full power) heats a thermal mass that cools towards a 22 °C room (τ = 90 s). The PID loop has a ramping working setpoint and alarm bits. The simulator answers exception 02 for unimplemented addresses, 03 for values outside its own range (e.g. a 500 °C setpoint), and 0B for a wrong unit id. With --simulate --option register_map=my_map.yaml, points that are not in the example layout get zero-initialised storage, so you can test your own map.

Connect your device

  1. Device setup: in the device's communications menu, enable Modbus and note its settings.
    • RTU (RS-485): set the unit (slave) address (1–247), baud rate, parity and stop bits. The server defaults to the Modbus serial default of 19200 baud, 8 data bits, even parity, 1 stop bit. Many devices ship with other settings (e.g. 9600 8N1); put your device's settings in the address. Wire the USB-RS485 adapter's A/B (D−/D+) lines to the device; vendors disagree on the A/B labels, so swap them if nothing answers. Connect the signal ground, and put 120 Ω termination at both ends of longer buses.
    • TCP: set the IP address. The port is 502 unless changed. Many TCP devices ignore the unit id. If yours does not, it is usually 1; the TCP implementation guide recommends 255 for directly addressed devices.
  2. Write a register map for your device from its Modbus manual. Copy the example and see Register map below.
  3. Test the connection:
    bash
    uvx labmcp-modbus --address tcp://192.168.1.20:502 --option register_map=~/maps/oven.yaml --checkuvx labmcp-modbus --address "serial:///dev/ttyUSB0?baudrate=9600&parity=N" --option unit_id=3 \    --option register_map=~/maps/controller.yaml --checkuvx labmcp-modbus --address "serial://COM4?baudrate=19200&parity=E" --option register_map=C:/maps/chiller.json --checkuvx labmcp-modbus --address "tcp://192.168.1.30:4001?framer=rtu" --check      # RTU through a transparent gateway
    --check connects, reads the map's first point as a probe and prints probe: ok: … or the error. More address parameters: stopbits=2, bytesize=7, framer=ascii (Modbus ASCII), timeout=1, retries=2.

Register map

yaml
device:                 # optional  name: Incubator oven  manufacturer: Example  model: X-100  unit_id: 1            # --option unit_id overrides it  word_order: big       # default for 32/64-bit points  byte_order: big
points:  chamber_temperature:    table: input        # holding | input | coil | discrete    address: 0          # 0-based protocol address ("30001" in the manual -> input 0)    type: int16         # uint16 | int16 | uint32 | int32 | float32 | float64 | bool    scale: 0.1          # value = raw * scale + offset    unit: °C    description: Chamber temperature  setpoint:    table: holding    address: 0          # "40001" -> holding 0    type: int16    scale: 0.1    unit: °C    writable: true    min: 20             # required for writable numbers: checked before sending    max: 60  mode:    table: holding    address: 1    writable: true    enum: {0: standby, 1: run}  heater_enable:    table: coil    address: 0    writable: true
safe_state:             # optional: run in order by apply_safe_state  - {point: heater_enable, value: false}  - {point: mode, value: standby}
FieldDefaultMeaning
table(required)holding (FC03/06/16), input (FC04, read-only), coil (FC01/05), discrete (FC02, read-only)
address(required)0-based protocol (PDU) address. Manual numbering: 4xxxx → holding xxxx − 1, 3xxxx → input, 1xxxx → discrete, 0xxxx → coil
typeuint16 (bool for coils/discretes)32-bit types use 2 registers, float64 uses 4. bool in a register means 0 = false, anything else = true
word_order / byte_orderbig / bigbig/big = ABCD (most significant register first). little/big = CDAB (common on PLCs). big/little = BADC. little/little = DCBA
scale, offset1, 0Engineering value = raw × scale + offset. Writes are rounded to the register's resolution and re-checked
unit, description""Shown to the agent
writablefalseOnly holding registers and coils can be writable
min, maxnoneEngineering-unit limits. Required for writable numeric points (unless enum is used)
enumnone{number: label} for integer points. Writes accept the label or the number

The server validates the map when it starts. Unknown fields (e.g. a misspelt maximum) and repeated keys (a second max, or a point defined twice) are errors rather than being silently ignored, so a typo can't remove a limit. Two writable points may not share a register (writing one would bypass the other's limits); read-only views of a writable register are fine. If the map is invalid, list_points shows the error and the device tools refuse to run. The server fails closed.

Add to your MCP client

Claude Code

bash
claude mcp add oven -- uvx labmcp-modbus --address tcp://192.168.1.20:502 --option register_map=/home/me/maps/oven.yaml

Claude Desktop / Cursor / Windsurf (claude_desktop_config.json, .cursor/mcp.json, …)

json
{  "mcpServers": {    "controller": {      "command": "uvx",      "args": [        "labmcp-modbus", "--address", "serial:///dev/ttyUSB0?baudrate=9600&parity=N",        "--option", "unit_id=1",        "--option", "register_map=/home/me/maps/controller.yaml",        "--option", "raw_writes=false"      ]    }  }}

Useful flags:

  • --read-only allows reads only. apply_safe_state stays available.
  • --option raw_writes=false removes write_register, write_registers and write_coil, so the agent can only write what the map allows. This is recommended once your map is complete.

Tools

ToolKindDescription
apply_safe_state🛑 safetyPut the device into the safe state defined in the register map (e.g. heater output off, controller to standby), writing each step in order and reading it back. Every step is attempted even if an earlier one fails. Call it immediately if anything looks wrong. all_ok is true only if every step was written AND read back with the requested value; a step the device acknowledged but ignored (e.g. in local mode) is not ok.
get_command_log👁 readReturn the most recent raw commands sent to / replies received from the instrument (newest last). Useful for debugging and for recording what was done.
get_connection_info👁 readReport which instrument is connected (identity, address, simulated or real), whether the server is read-only, and the active safety limits. Call this first.
list_points👁 readDescribe the loaded register map: device, every named point (table, 0-based address, type, scaling, unit, writable, min/max, enum) and the safe-state steps. Works without a connection.
read_coils👁 readRead coils (FC01): single-bit outputs such as run/stop or relay states.
read_discrete_inputs👁 readRead discrete inputs (FC02): single-bit, read-only status such as alarms or limit switches.
read_points👁 readRead named points from the register map, decoded and scaled into engineering units (e.g. process_temperature = 25.1 °C). A point that cannot be read gets an error instead of failing the whole call.
read_registers👁 readRead raw holding or input registers (unsigned 16-bit), optionally decoded as int16, 32-bit or 64-bit values. For exploring a device; prefer read_points when a register map describes it.
reconnect🛑 safetyClose and re-open the connection to the instrument (e.g. after it was power cycled or a cable was re-plugged).
write_coil⚠️ hazardSwitch one raw coil (FC05). Coils often start or stop equipment (heaters, pumps, motors); mapped coils are refused here (use write_point).
write_point⚠️ hazardWrite a named point from the register map (setpoint, mode, output enable...). The value is checked against the point's writable flag, min/max or enum BEFORE sending, converted to raw registers, written, then read back. Changing setpoints and outputs acts on real equipment. If the write succeeds but the read-back fails, read_back_error says why.
write_register⚠️ hazardWrite one raw holding register (FC06). No scaling or limits are applied, so only use it for addresses the register map does not describe (mapped addresses are refused: use write_point). Returns a read-back if the register is readable.
write_registers⚠️ hazardWrite consecutive raw holding registers (FC16), e.g. both halves of a 32-bit value. No scaling or limits are applied; mapped addresses are refused (use write_point).

get_connection_info, get_command_log and reconnect are built into every LabMCP server. apply_safe_state is listed only when the register map defines a safe_state.

Safety limits

This server has no global --limit values: a generic Modbus client can't know what a register means. The protections come from the register map and the server:

ProtectionWhere
writable: false (default)write_point refuses the point
min / max / enum per pointwrite_point refuses out-of-range values before sending, and again after rounding to the register resolution (integer or float32)
Mapped-address protectionwrite_register(s) / write_coil refuse any address that overlaps a mapped point
--option raw_writes=falseRemoves the raw write tools entirely
--read-onlyRemoves every write tool. apply_safe_state remains
safe_state in the mapapply_safe_state writes each step in order and reads it back. Every step is attempted even if one fails. A step is ok only if the read-back matches, so a device that acknowledges but ignores writes (local/keypad mode) is reported, not trusted
Request bounds1–125 registers (FC03/04), 1–2000 bits (FC01/02), 1–123 registers (FC16) per request, as in the spec
No broadcastUnit id 0 is refused on serial lines: it would write to every device, and devices do not reply to broadcasts

Example prompts

  • "What's the chamber temperature and output power right now? Show every point with its unit."
  • "Ramp the controller to 55 °C at 2 °C/min, switch it to auto, enable the heater, and tell me when it's within 0.5 °C of setpoint."
  • "Set the high alarm to 70 °C, then check whether any alarm or sensor-fault bits are active."
  • "Read holding registers 100–109 and decode them as float32 (try both word orders). I'm mapping a new chiller."
  • "Something's wrong: put the controller in its safe state and confirm the heater is off."

Notes

  • Addresses are 0-based on the wire. Manuals often use 1-based "Modicon" numbers (40001 = holding 0). If every read is off by one register, the map uses the wrong convention.
  • Word order is not standardised for 32-bit values: the Modbus spec only defines byte order within a register. If a float or 32-bit value looks absurd, try word_order: little. read_registers with decode_as helps you find the right order.
  • A float point that reads NaN or infinity (many devices use NaN as "no value", e.g. a sensor fault) comes back with value: null and an error; read_registers with decode_as shows it as "nan"/"inf".
  • write_point uses FC06 for single-register points, FC16 for multi-register points and FC05 for coils. A few devices accept only FC16 even for single registers. For those, map the value as part of a multi-register point or report it so we can add an option.
  • Some controllers save written parameters to non-volatile memory, which survives only a limited number of write cycles. Don't have the agent rewrite setpoints in a tight loop. Check whether the manual offers a RAM-only or remote setpoint register.
  • Reading is normally side-effect free, but a few devices clear counters or alarms when they are read. Leave such registers out of the map or mark them in description.
  • Modbus TCP devices often accept only a few simultaneous connections. Close other SCADA or logging clients if the connection is refused.
  • Timeouts nearly always mean a wrong unit id, baud rate, parity or A/B wiring. Exception 02 means an address the device does not implement. Exception 03 means the device rejected the value by its own internal limits.
  • Works with pymodbus 3.8 or newer (the unit keyword changed from slave= to device_id= in 3.10; both are handled).
  • The bundled map is an illustrative example. Contributions of real device maps are welcome: include the manual title and revision the addresses came from.

Hardware verification

ModelFirmwareInterfaceVerified byDate
none yet: be the first

Source: servers/protocols/modbus/README.md at commit 46545ea

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.3LatestSep 27, 2026
  2. v0.1.1Sep 26, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts