Open-source MCP servers that let AI agents operate real lab instruments, with safety limits, read-only modes, audit trails, and a simulator for every instrument.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
- !Install pipes a remote script into a shell (curl | sh)
claude mcp add lab-instrument-mcps -- uvx labmcp-mettler-toledo{
"mcpServers": {
"lab-instrument-mcps": {
"command": "uvx",
"args": ["labmcp-mettler-toledo"]
}
}
}MCP Servers overview
# LabMCP: Let AI Assistants Run Your Lab Instruments
[](LICENSE)
[](https://www.python.org/)
[](https://gofastmcp.com)
[](https://modelcontextprotocol.io)
<!-- COUNTS:START -->
[](#-supported-instruments) [](#-supported-instruments)
<!-- COUNTS:END -->
[](https://github.com/K-Dense-AI/lab-instrument-mcps/actions/workflows/ci.yml)
[](docs/clients.md)
**LabMCP lets an AI assistant such as Claude operate your laboratory instruments.** You describe what you want in plain language, and the assistant weighs, heats, stirs, pumps, measures and logs for you. It stays inside safety limits you set, keeps a record of every command, and has a practice mode that needs no hardware.
It supports balances, hotplate stirrers, syringe pumps, spectrometers, mass spectrometers, potentiostats, lock-in amplifiers, temperature controllers, vacuum gauges, flow controllers, biosensors, clinical analyzers and more. **You don't need to know how to program.** Setup means installing one free helper program and pasting a few lines into your AI app's settings.
Free and open source, built by [K-Dense](https://www.k-dense.ai).
```text
You: Tare the balance, then heat the stirrer to 60 °C at 400 rpm and log the pH every
30 s until it's stable. Tell me when to add the reagent.
Assistant: [tares the balance → sets stirring to 400 rpm → sets heating to 60 °C → logs pH …]
"pH has been 7.41 ± 0.01 for 3 minutes. Ready for the reagent."
```
> ⭐ **Help other scientists find this.** If LabMCP is useful to you, please star the repo.
---
## 📋 Contents
- [How it works](#-how-it-works)
- [Try it in 10 minutes (no instrument needed)](#-try-it-in-10-minutes-no-instrument-needed)
- [Supported instruments](#-supported-instruments)
- [Connect your real instrument](#-connect-your-real-instrument)
- [Safety](#%EF%B8%8F-safety)
- [What every connector includes](#-what-every-connector-includes)
- [Example requests](#-example-requests)
- [FAQ](#-faq)
- [Contributing](#-contributing)
- [Roadmap](#-roadmap)
---
## 💡 How it works
```text
You ──type──▶ AI app ──▶ LabMCP connector ──USB / serial / network cable──▶ Instrument
(Claude, (runs on the computer
Cursor, …) attached to the instrument)
```
- **The AI app** is where you type requests, e.g. Claude Desktop.
- **A LabMCP connector** is a small program that knows one family of instruments and its command language, so the AI never has to guess it. You add one connector per type of instrument. (Technically these are *MCP servers*, which is the term you'll see in the tables and docs.)
- **MCP** ([Model Context Protocol](https://modelcontextprotocol.io)) is the open standard that lets AI apps plug into tools like these. Think of it as USB for AI.
- The AI can only use the **actions** a connector offers, like "tare", "set temperature" or "read pH". In the docs these actions are called *tools*. The connector checks every request against your limits and refuses anything unsafe before it reaches the instrument.
---
## 🚀 Try it in 10 minutes (no instrument needed)
Each connector has a **practice mode** (a *simulator*) that behaves like the real instrument and gives realistic replies. Nothing is connected, so nothing can go wrong.
**You need:** a Mac, Windows or Linux computer, and an AI app that supports MCP. [Claude Desktop](https://claude.ai/download) is the easiest place to start.
### Step 1: Install `uv` (once)
`uv` is a free tool that downloads and runs LabMCP for you. Open a terminal:
- **Mac:** press ⌘ Space, type *Terminal*, press Enter.
- **Windows:** open the Start menu, type *PowerShell*, press Enter.
Paste the line for your system and press Enter:
```bash
# Mac or Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
```
```powershell
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```
Close the terminal and open it again so it finds the new program.
### Step 2: Add a practice balance to your AI app
In **Claude Desktop**, go to **Settings → Developer → Edit Config**. This opens a file called `claude_desktop_config.json`. Paste the following into it and save. If the file already has an `"mcpServers"` section, add only the `"balance"` line inside it.
```json
{
"mcpServers": {
"balance": { "command": "uvx", "args": ["labmcp-mettler-toledo", "--simulate"] }
}
}
```
Quit Claude Desktop completely, then reopen it.
> **Mac tip:** if Claude reports that it can't find `uvx`, run `which uvx` in Terminal and replace `"uvx"` in the file with the full path it prints (usually `/Users/<your-name>/.local/bin/uvx`).
**Using a different app?** For Claude Code, run `claude mcp add balance -- uvx labmcp-mettler-toledo --simulate` in a terminal. For Cursor, VS Code, Codex and Windsurf, see [docs/clients.md](docs/clients.md).
### Step 3: Ask
> *"What instrument is connected? Tare it, then log the weight every second for 10 seconds."*
The first request can take a minute while the connector downloads. Your AI app will usually ask your permission before it takes an action. Say yes.
**Want a whole lab?** [`examples/`](examples/) sets up six practice instruments at once (balance, stirrer, pH probe, syringe pump, potentiostat and spectrometer).
---
## 📦 Supported instruments
Find your instrument below and click its name. Each page covers the settings to change on the instrument itself, the safety limits you can set, and everything the AI can do with it.
**Reading the tables:**
- **Interface** is the cable or connection the instrument uses.
- **Tools** is how many different actions the AI can take.
- **Install** is the name to put in your AI app's settings (the part after `uvx`).
- **Status:** 🧪 *simulated* means built from the manufacturer's published manual and tested thoroughly in practice mode, but not yet confirmed on a real instrument by a user. ✅ *hardware-verified* means someone has confirmed it on the real instrument. **If you own one of these instruments, you can [help verify it](CONTRIBUTING.md#1-test-a-server-on-real-hardware--most-needed). No coding needed.**
<!-- CATALOG:START -->
### 🧬 Biology & Life Sciences
| Server | Instruments | Interface | Tools | Status | Install |
|---|---|---|---|---|---|
| [**Atlas Scientific EZO Sensors**](servers/biology/atlas-ezo-sensors)<br><sub>Read pH, ORP, dissolved oxygen, conductivity/TDS/salinity, temperature, humidity, CO2 or pressure; calibrate, set temperature compensation, log series.</sub> | Atlas Scientific: EZO-pH, EZO-ORP, EZO-DO, EZO-EC … | UART (USB-serial adapter), Ethernet (serial bridge) | 13 | 🧪 simulated | `uvx labmcp-atlas-ezo` |
| [**Micro-Manager Microscope**](servers/biology/micro-manager)<br><sub>Snap images (stats + preview + TIFF), z-stacks and time-lapses, move XY/Z within step and soft limits, channel/objective presets, exposure, shutter, autofocus.</sub> | Micro-Manager (open source; hundreds of camera, stage, filter and light-source vendors): Any microscope with a Micro-Manager hardware configuration (.cfg), Micro-Manager demo configuration | USB, Serial, Camera Link / CoaXPress / GigE (through Micro-Manager device adapters) | 19 | 🧪 simulated | `uvx labmcp-micro-manager` |
| [**New Era Syringe Pump**](servers/biology/new-era-syringe-pump)<br><sub>Set the syringe (presets or diameter), infuse or withdraw an exact volume at a set rate, track dispensed volume, stop.</sub> | New Era Pump Systems: NE-1000, NE-1002X, NE-1010, NE-4000 … | RS-232, USB (RS-232 adapter), Serial-to-Ethernet | 11 | 🧪 simulated | `uvx labmcp-new-era` |
| [**Opentrons OT-2 / Flex**](servers/biology/opentrons)<br><sub>Upload and analyze protocols, review deck layout, start/pause/stop/resume runs, track progress, home, lights, read pipettes and modules, switch modules off.</sub> | Opentrons: Flex, OT-2 | Ethernet, Wi-Fi, USB (network over USB) | 18 | 🧪 simulated | `uvx labmcp-opentrons` |
| [**Tecan Cavro Syringe Pump**](servers/biology/tecan-cavro-pump)<br><sub>Initialize, aspirate and dispense microlitre volumes at set flow rates, switch valve ports, read plunger/valve status, terminate moves.</sub> | Tecan: Cavro XLP 6000, Cavro XMP 6000, Cavro XCalibur | RS-232, RS-485 (via adapter), Serial-to-Ethernet | 9 | 🧪 simulated | `uvx labmcp-cavro` |
### ⚗️ Chemistry
| Server | Instruments | Interface | Tools | Status | Install |
|---|---|---|---|---|---|
| [**IKA Hotplate & Overhead Stirrer**](servers/chemistry/ika-stirrer)<br><sub>Read plate/probe temperature and speed, set and start heating and stirring, hardware watchdog, wait for temperature, stop all.</sub> | IKA: C-MAG HS 7 control, IKA Plate (RCT digital), EUROSTAR 60 control, EUROSTAR 100 control | RS-232, USB (virtual COM) | 14 | 🧪 simulated | `uvx labmcp-ika` |
| [**JULABO Circulator**](servers/chemistry/julabo-circulator)<br><sub>Read bath/external temperature and heating power, set setpoint, start/stop tempering, decode status and alarms, wait for temperature.</sub> | JULABO: CORIO CD, CORIO CP, MAGIO MS, DYNEO DD | USB (virtual COM), RS-232 | 10 | 🧪 simulated | `uvx labmcp-julabo` |
| [**LC-MS Worklist Builder**](servers/chemistry/ms-worklist)<br><sub>Build, randomise, validate, convert and export LC-MS sample queues as vendor import files (never starts a run).</sub> | Multi-vendor: Waters MassLynx 4.x, SCIEX OS, Agilent MaWhat people ask about lab-instrument-mcps
What is K-Dense-AI/lab-instrument-mcps?
+
K-Dense-AI/lab-instrument-mcps is mcp servers for the Claude AI ecosystem. Open-source MCP servers that let AI agents operate real lab instruments, with safety limits, read-only modes, audit trails, and a simulator for every instrument. It has 5 GitHub stars and its last recorded update is dated 2026-09-26.
How do I install lab-instrument-mcps?
+
You can install lab-instrument-mcps by cloning the repository (https://github.com/K-Dense-AI/lab-instrument-mcps) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is K-Dense-AI/lab-instrument-mcps safe to use?
+
Our security agent has analyzed K-Dense-AI/lab-instrument-mcps and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains K-Dense-AI/lab-instrument-mcps?
+
K-Dense-AI/lab-instrument-mcps is maintained by K-Dense-AI. The last recorded GitHub activity is dated 2026-09-26, with 0 open issues.
Are there alternatives to lab-instrument-mcps?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy lab-instrument-mcps to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/k-dense-ai-lab-instrument-mcps)<a href="https://claudewave.com/repo/k-dense-ai-lab-instrument-mcps"><img src="https://claudewave.com/api/badge/k-dense-ai-lab-instrument-mcps" alt="Featured on ClaudeWave: K-Dense-AI/lab-instrument-mcps" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
The fastest path to AI-powered full stack observability, even for lean teams.