# Tecan Cavro Syringe Pump (pypi · labmcp-cavro)

MCP server for Tecan Cavro syringe pumps (XLP 6000, XMP 6000, XCalibur) over the DT protocol.

- Trust score: 83/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-cavro`: 83/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-cavro`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-30.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 2 of 17 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to K-Dense-AI/lab-instrument-mcps).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1077 tokens (~119/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Tecan Cavro Syringe Pump MCP server?

Tecan Cavro Syringe Pump runs locally as a PyPI package, launched with uvx labmcp-cavro. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add k-dense-ai-labmcp-cavro -- uvx labmcp-cavro
```

### Cursor

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-cavro": {
      "command": "uvx",
      "args": [
        "labmcp-cavro"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "k-dense-ai-labmcp-cavro": {
      "command": "uvx",
      "args": [
        "labmcp-cavro"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add k-dense-ai-labmcp-cavro -- uvx labmcp-cavro
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "k-dense-ai-labmcp-cavro": {
      "type": "local",
      "command": [
        "uvx",
        "labmcp-cavro"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add k-dense-ai-labmcp-cavro --command uvx --arg labmcp-cavro
```

### Hermes

```yaml
mcp_servers:
  k-dense-ai-labmcp-cavro:
    command: "uvx"
    args: ["labmcp-cavro"]
```

### Netclaw

```json
{
  "McpServers": {
    "k-dense-ai-labmcp-cavro": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "labmcp-cavro"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add k-dense-ai-labmcp-cavro -t stdio -c uvx -a labmcp-cavro
```

### Other

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-cavro": {
      "command": "uvx",
      "args": [
        "labmcp-cavro"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-30 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-29 (score 68, −14)

- [security regression] Malware scan: pass → unverified

### 2026-09-28 (score 82, +43)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 39, 0)

- [functional] Package version: 0.1.0 → 0.1.3

### 2026-09-26 (score 39, −32)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.0 → 0.1.2
- [functional] Package version: 0.1.0 → 0.1.1

### 2026-09-25 (score 71)

First indexed and scored.

## MCP tools (9)

### `get_connection_info` (~40 tokens)

Get Connection Info

Report which instrument is connected (identity, address, simulated or real),
whether the server is read-only, and the active safety limits. Call this first.

### `get_command_log` (~46 tokens)

Get Command Log

Return the most recent raw commands sent to / replies received from the
instrument (newest last). Useful for debugging and for recording what was done.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (array)

### `reconnect` (~35 tokens)

Reconnect

Close and re-open the connection to the instrument (e.g. after it was power
cycled or a cable was re-plugged).

### `get_status` (~45 tokens)

Get Status

Report whether the pump is ready or busy, any error (decoded), the plunger position as the
volume in the syringe, the valve position, resolution mode and current top speed.

Output parameters:

- `error` (string): Meaning of the error code
- `error_code` (integer): Error code from the status byte (0 = none)
- `plunger_position_steps` (integer)
- `plunger_position_ul` (number): Volume currently drawn into the syringe
- `ready` (boolean): True when the pump accepts new move commands (Q status bit 5)
- `resolution_mode` (integer): 0 = standard (N0), 1 = fine positioning (N1), 2 = microstep (N2)
- `steps_per_stroke` (integer): Plunger increments for a full stroke in the current mode
- `syringe_ul` (number)
- `timestamp` (string)
- `top_speed_flow_ul_s` (number): Flow rate the current top speed corresponds to
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

### `initialize` (~149 tokens)

Initialize

Initialize the pump: drive the plunger to the top of the syringe (expelling its contents
through the valve), set that as position 0 and home the valve. Needed after power-up, a plunger
overload or `terminate`. Route the valve output to waste first. Takes a few seconds.

Input parameters:

- `force` (string): Plunger force against the syringe top; auto picks it from the syringe size
- `input_port`: Distribution valves: input port
- `output_port`: Distribution valves: output port
- `valve_direction` (string): Valve homing/port numbering: cw (Z command), ccw (Y), or no_valve (W, plunger only)

Output parameters:

- `error` (string): Meaning of the error code
- `error_code` (integer): Error code from the status byte (0 = none)
- `plunger_position_steps` (integer)
- `plunger_position_ul` (number): Volume currently drawn into the syringe
- `ready` (boolean): True when the pump accepts new move commands (Q status bit 5)
- `resolution_mode` (integer): 0 = standard (N0), 1 = fine positioning (N1), 2 = microstep (N2)
- `steps_per_stroke` (integer): Plunger increments for a full stroke in the current mode
- `syringe_ul` (number)
- `timestamp` (string)
- `top_speed_flow_ul_s` (number): Flow rate the current top speed corresponds to
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

### `set_valve` (~89 tokens)

Set Valve

Turn the valve to a named position (3/4-port valves) or to a numbered port (distribution
valves). In bypass the plunger cannot move. Returns the new status.

Input parameters:

- `direction` (string): Distribution valves: rotation direction to the port
- `port`: Distribution valves: port number
- `position`: Non-distribution valves: input, output, bypass or extra

Output parameters:

- `error` (string): Meaning of the error code
- `error_code` (integer): Error code from the status byte (0 = none)
- `plunger_position_steps` (integer)
- `plunger_position_ul` (number): Volume currently drawn into the syringe
- `ready` (boolean): True when the pump accepts new move commands (Q status bit 5)
- `resolution_mode` (integer): 0 = standard (N0), 1 = fine positioning (N1), 2 = microstep (N2)
- `steps_per_stroke` (integer): Plunger increments for a full stroke in the current mode
- `syringe_ul` (number)
- `timestamp` (string)
- `top_speed_flow_ul_s` (number): Flow rate the current top speed corresponds to
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

### `aspirate_ul` (~116 tokens)

Aspirate Ul

Draw `volume_ul` into the syringe at `flow_ul_s` through the current (or given) valve port,
and wait until the move has finished. The pump must be initialized and have room for the volume.

Input parameters:

- `flow_ul_s` (number): Plunger flow rate, µL/s
- `port`: Distribution valves: port to turn to first
- `valve`: Turn the valve here first (e.g. 'input')
- `volume_ul` (number, required): Volume to draw into the syringe, µL

Output parameters:

- `action` (string)
- `duration_s` (number)
- `flow_ul_s` (number): Flow at the commanded top speed (ramps make the average slightly lower)
- `moved_ul` (number): Volume actually commanded after rounding to whole plunger steps
- `plunger_position_ul` (number)
- `requested_ul` (number)
- `steps` (integer)
- `terminated` (boolean): True if `terminate` interrupted the move
- `timestamp` (string)
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

### `dispense_ul` (~114 tokens)

Dispense Ul

Push `volume_ul` out of the syringe at `flow_ul_s` through the current (or given) valve port,
and wait until the move has finished. The syringe must contain at least that volume.

Input parameters:

- `flow_ul_s` (number): Plunger flow rate, µL/s
- `port`: Distribution valves: port to turn to first
- `valve`: Turn the valve here first (e.g. 'output')
- `volume_ul` (number, required): Volume to push out of the syringe, µL

Output parameters:

- `action` (string)
- `duration_s` (number)
- `flow_ul_s` (number): Flow at the commanded top speed (ramps make the average slightly lower)
- `moved_ul` (number): Volume actually commanded after rounding to whole plunger steps
- `plunger_position_ul` (number)
- `requested_ul` (number)
- `steps` (integer)
- `terminated` (boolean): True if `terminate` interrupted the move
- `timestamp` (string)
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

### `terminate` (~44 tokens)

Terminate

Stop any plunger move, loop or delay immediately (DT command T). A valve move in progress
still completes. Re-initialize afterwards: the plunger may have lost steps.

Output parameters:

- `error` (string): Meaning of the error code
- `error_code` (integer): Error code from the status byte (0 = none)
- `plunger_position_steps` (integer)
- `plunger_position_ul` (number): Volume currently drawn into the syringe
- `ready` (boolean): True when the pump accepts new move commands (Q status bit 5)
- `resolution_mode` (integer): 0 = standard (N0), 1 = fine positioning (N1), 2 = microstep (N2)
- `steps_per_stroke` (integer): Plunger increments for a full stroke in the current mode
- `syringe_ul` (number)
- `timestamp` (string)
- `top_speed_flow_ul_s` (number): Flow rate the current top speed corresponds to
- `top_speed_pulses_s` (integer)
- `valve_position` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro#diagnostics

## Score history

- 2026-09-30: 83
- 2026-09-29: 68
- 2026-09-28: 82
- 2026-09-27: 39
- 2026-09-26: 39
- 2026-09-25: 71

## Common questions

### What is the Tecan Cavro Syringe Pump MCP server?

Tecan Cavro Syringe Pump is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-cavro. MCP server for Tecan Cavro syringe pumps (XLP 6000, XMP 6000, XCalibur) over the DT protocol. This page covers its PyPI package (labmcp-cavro).

### Is the Tecan Cavro Syringe Pump MCP server safe to use?

Tecan Cavro Syringe Pump scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 30 September 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Tecan Cavro Syringe Pump MCP server expose?

Tecan Cavro Syringe Pump exposes 9 tools: get_connection_info, get_command_log, reconnect, get_status, initialize, and 4 more. Their descriptions and schemas cost roughly 678 tokens of context every time the server is loaded.

### Is the Tecan Cavro Syringe Pump MCP server still maintained?

Tecan Cavro Syringe Pump is still listed as active in the MCP registry. We last reached this channel on 30 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Tecan Cavro Syringe Pump MCP server under?

Tecan Cavro Syringe Pump declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/labmcp-cavro/
- Socket report: https://socket.dev/pypi/package/labmcp-cavro
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/biology/tecan-cavro-pump
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-cavro/labmcp-cavro