# Tecan Cavro Syringe Pump

Controls Tecan Cavro OEM syringe pumps over the DT protocol. Lets an agent aspirate microvolumes, switch valve ports, and check pump telemetry.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 23
- Author: K-Dense-AI
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/HEAD/servers/biology/tecan-cavro-pump
- Updated: 2026-09-26
- HTML: https://affpapa.org/en/nevibecode/mcp/tecan-cavro-syringe-pump

## What it does

The `labmcp-cavro` package connects an AI agent to OEM syringe pumps including Cavro XLP 6000, XMP 6000, and XCalibur units. Commands travel over the Cavro Data Terminal (DT) standard through RS-232, RS-485, or serial-to-Ethernet interfaces. It supports valveless configurations alongside distribution and multi-port valves.

Available tools handle liquid intake (`aspirate_ul`), dispensing (`dispense_ul`), and port switching (`set_valve`). The `terminate` tool immediately stops the plunger mechanism if a line stalls. Built-in guardrails restrict flow rates to 500 µL/s and volume per action to 5000 µL. Passing `--read-only` disables all motor triggers while keeping diagnostic telemetry open.

Pumps cannot detect their mounted syringe size, so `--option syringe_ul` and `--option model` remain mandatory arguments on physical benches. The codebase has passed wire-level simulation runs but lacks physical hardware verification. You can spin up an emulated device right away using the `--simulate` flag.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `LABMCP_ADDRESS`, `LABMCP_SIMULATE`, `LABMCP_READ_ONLY`, `LABMCP_LIMITS` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env LABMCP_ADDRESS=<LABMCP_ADDRESS> --env LABMCP_SIMULATE=<LABMCP_SIMULATE> --env LABMCP_READ_ONLY=<LABMCP_READ_ONLY> --env LABMCP_LIMITS=<LABMCP_LIMITS> --transport stdio tecan-cavro-pump -- uvx labmcp-cavro
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-cavro <command>

### Codex

**Platform CLI**
```bash
codex mcp add tecan-cavro-pump --env LABMCP_ADDRESS=<LABMCP_ADDRESS> --env LABMCP_SIMULATE=<LABMCP_SIMULATE> --env LABMCP_READ_ONLY=<LABMCP_READ_ONLY> --env LABMCP_LIMITS=<LABMCP_LIMITS> -- uvx labmcp-cavro
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-cavro <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "tecan-cavro-pump": {
            "command": "uvx",
            "args": [
                "labmcp-cavro"
            ],
            "env": {
                "LABMCP_ADDRESS": "<LABMCP_ADDRESS>",
                "LABMCP_SIMULATE": "<LABMCP_SIMULATE>",
                "LABMCP_READ_ONLY": "<LABMCP_READ_ONLY>",
                "LABMCP_LIMITS": "<LABMCP_LIMITS>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-cavro <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "tecan-cavro-pump": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "labmcp-cavro"
            ],
            "env": {
                "LABMCP_ADDRESS": "<LABMCP_ADDRESS>",
                "LABMCP_SIMULATE": "<LABMCP_SIMULATE>",
                "LABMCP_READ_ONLY": "<LABMCP_READ_ONLY>",
                "LABMCP_LIMITS": "<LABMCP_LIMITS>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-cavro <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e LABMCP_ADDRESS=<LABMCP_ADDRESS> -e LABMCP_SIMULATE=<LABMCP_SIMULATE> -e LABMCP_READ_ONLY=<LABMCP_READ_ONLY> -e LABMCP_LIMITS=<LABMCP_LIMITS> tecan-cavro-pump uvx labmcp-cavro
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from labmcp-cavro <command>

## When to use it
- draw and dispense precise microlitre volumes at controlled speeds
- switch distribution or multi-port valves between liquid lines
- halt plunger travel instantly during overpressure or stall conditions
- read plunger position, error codes, and operational status

## Example prompts
- Initialize the pump and prime it by drawing 1000 µL through the intake and dispensing to waste three times.
- Draw 150 µL from port 3 at 20 µL/s and dispense 50 µL into port 5.
- Check current status: report syringe volume and the active valve port.

## Similar
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5585
- [arxiv-mcp-server](https://affpapa.org/en/nevibecode/mcp/arxiv-mcp-server.md) — MCP server · ★ 3235
- [PaperBanana](https://affpapa.org/en/nevibecode/mcp/paperbanana.md) — MCP server · ★ 2418
- [MATLAB MCP Server](https://affpapa.org/en/nevibecode/mcp/matlab-mcp-server.md) — MCP server · ★ 1723
- [Hex Research](https://affpapa.org/en/nevibecode/mcp/hex-research.md) — MCP server · ★ 584
- [DocsAgent — Zotero, Obsidian & Apple Notes MCP Server](https://affpapa.org/en/nevibecode/mcp/docsagent-zotero-obsidian-apple-notes-mcp-server.md) — MCP server · ★ 578

From the same set: [k-dense-ai/lab-instrument-mcps](https://affpapa.org/en/nevibecode/by/k-dense-ai/lab-instrument-mcps.md) — 28 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md