# Ocean Insight Spectrometer (pypi · labmcp-ocean-spectrometer)

MCP server for Ocean Insight / Ocean Optics spectrometers (python-seabreeze).

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

## Components

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

## Channel facts

- Registry: `pypi`
- Package: `labmcp-ocean-spectrometer`
- Version: `0.1.2`
- 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 19 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**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2108 tokens (~131/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% 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.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 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 Ocean Insight Spectrometer MCP server?

Ocean Insight Spectrometer runs locally as a PyPI package, launched with uvx labmcp-ocean-spectrometer. 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-ocean-spectrometer -- uvx labmcp-ocean-spectrometer
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add k-dense-ai-labmcp-ocean-spectrometer -- uvx labmcp-ocean-spectrometer
```

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-29 (score 67, −15)

- [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, −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] First check of Schema quality: unverified
- [functional] Package version: 0.1.1 → 0.1.2

### 2026-09-26 (score 71)

First indexed and scored.

## MCP tools (16)

### `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).

### `list_spectrometers` (~53 tokens)

List Spectrometers

List the Ocean spectrometers seabreeze can see (model, serial number, whether open) and
which one this server is connected to. Use a serial number as `--address` to pick one.

Output parameters:

- `result` (array)

### `get_device_info` (~40 tokens)

Get Device Info

Model, serial, pixel count, wavelength range, integration-time limits, saturation level,
supported corrections, TEC presence, and which dark/reference spectra are stored.

Output parameters:

- `backend` (string)
- `dark_stored`: Timestamp of the stored dark, if any
- `electric_dark_correction` (boolean)
- `has_tec` (boolean)
- `integration_time_max_ms` (number)
- `integration_time_min_ms` (number)
- `integration_time_ms` (number)
- `model` (string)
- `nonlinearity_correction` (boolean)
- `pixels` (integer)
- `reference_stored`: Timestamp of the stored reference, if any
- `saturation_counts` (number): max_intensity: raw counts at full scale
- `serial` (string)
- `wavelength_max_nm` (number)
- `wavelength_min_nm` (number)

### `set_integration_time` (~57 tokens)

Set Integration Time

Set the detector integration time (ms), within the device limits from `get_device_info`.
Stored dark/reference spectra become unusable until re-taken at the new time.

Input parameters:

- `integration_time_ms` (number, required): Integration time in ms

### `acquire_spectrum` (~260 tokens)

Acquire Spectrum

Acquire an intensity spectrum (raw counts) with optional averaging, boxcar smoothing and
corrections. Returns downsampled (wavelength, counts), summary statistics, the most
prominent peaks with FWHM, and a saturation check; `save_path` writes the full spectrum to a
new .csv file (an existing file is never overwritten).

Input parameters:

- `boxcar_half_width` (integer): Boxcar smoothing: pixels averaged on EACH side (0 = off)
- `correct_dark_counts` (boolean): Subtract the mean of the optically masked (electric dark) pixels
- `correct_nonlinearity` (boolean): Apply the EEPROM nonlinearity correction
- `max_points` (integer): Maximum points returned (bin-averaged)
- `num_peaks` (integer): Number of peaks to report
- `save_path`: Optional new .csv file for the full-resolution data (existing files are not overwritten)
- `scans_to_average` (integer): Spectra averaged together
- `subtract_stored_dark` (boolean): Subtract the stored dark spectrum (same settings required)
- `wavelength_max_nm`: Only report/search below this wavelength (nm)
- `wavelength_min_nm`: Only report/search above this wavelength (nm)

Output parameters:

- `boxcar_half_width` (integer)
- `correct_dark_counts` (boolean)
- `correct_nonlinearity` (boolean)
- `dark_subtracted` (boolean)
- `integration_time_ms` (number)
- `intensity_counts` (array): Bin-averaged counts (downsampled)
- `max_at_nm` (number)
- `max_counts` (number)
- `mean_counts` (number)
- `min_counts` (number)
- `model` (string)
- `peak_raw_percent_of_saturation` (number): Highest raw count in any scan, % of saturation
- `peaks` (array): Most prominent peaks, found on the full-resolution spectrum
- `pixels` (integer)
- `points_returned` (integer)
- `saturated` (boolean)
- `saturated_pixels` (integer)
- `saturation_counts` (number)
- `saved_to`
- `scans_to_average` (integer)
- `serial` (string)
- `timestamp` (string)
- `warnings` (array)
- `wavelength_nm` (array): Bin-averaged wavelengths (downsampled to max_points)

### `store_dark_reference` (~138 tokens)

Store Dark Reference

Record and store a DARK spectrum (kept in memory) for absorbance/transmittance.
BEFORE calling, ask the user to BLOCK THE LIGHT PATH (close the shutter, switch the lamp off
or cap the fiber) and wait for confirmation. Uses the present integration time.

Input parameters:

- `boxcar_half_width` (integer): Boxcar smoothing: pixels averaged on EACH side (0 = off)
- `correct_dark_counts` (boolean): Electric-dark correction (use the same later)
- `correct_nonlinearity` (boolean): Nonlinearity correction (use the same later)
- `scans_to_average` (integer): Spectra averaged together

Output parameters:

- `boxcar_half_width` (integer)
- `correct_dark_counts` (boolean)
- `correct_nonlinearity` (boolean)
- `integration_time_ms` (number)
- `kind` (string)
- `max_at_nm` (number)
- `max_counts` (number)
- `mean_counts` (number)
- `peak_raw_percent_of_saturation` (number)
- `saturated_pixels` (integer)
- `scans_to_average` (integer)
- `timestamp` (string)
- `warnings` (array)

### `store_reference` (~129 tokens)

Store Reference

Record and store the REFERENCE (100 % transmission) spectrum in memory. BEFORE calling,
ask the user to put the BLANK (solvent-filled or empty cuvette) in the beam with the light on,
and wait for confirmation. Use the same settings as the dark.

Input parameters:

- `boxcar_half_width` (integer): Boxcar smoothing: pixels averaged on EACH side (0 = off)
- `correct_dark_counts` (boolean): Must match the stored dark
- `correct_nonlinearity` (boolean): Must match the stored dark
- `scans_to_average` (integer): Spectra averaged together

Output parameters:

- `boxcar_half_width` (integer)
- `correct_dark_counts` (boolean)
- `correct_nonlinearity` (boolean)
- `integration_time_ms` (number)
- `kind` (string)
- `max_at_nm` (number)
- `max_counts` (number)
- `mean_counts` (number)
- `peak_raw_percent_of_saturation` (number)
- `saturated_pixels` (integer)
- `scans_to_average` (integer)
- `timestamp` (string)
- `warnings` (array)

### `measure_absorbance` (~195 tokens)

Measure Absorbance

Measure the absorbance spectrum A = -log10((S - D) / (R - D)) of the sample now in the
beam, using the stored dark D and reference R (same settings). Ask the user to insert the
sample first. Also returns values at `wavelengths_nm` and the absorbance maxima.

Input parameters:

- `max_points` (integer): Maximum points returned (bin-averaged)
- `num_peaks` (integer): Number of peaks to report
- `save_path`: Optional new .csv file for the full-resolution data (existing files are not overwritten)
- `scans_to_average`: Spectra averaged (default: as the reference)
- `wavelength_max_nm`: Only report/search below this wavelength (nm)
- `wavelength_min_nm`: Only report/search above this wavelength (nm)
- `wavelengths_nm`: Wavelengths (nm) at which to report interpolated values

Output parameters:

- `at_wavelengths` (array)
- `dark_timestamp` (string)
- `integration_time_ms` (number)
- `kind` (string)
- `max_at_nm`
- `max_value`
- `peaks` (array): Absorbance maxima, or transmittance minima (dips)
- `pixels` (integer)
- `points_returned` (integer)
- `reference_timestamp` (string)
- `saved_to`
- `scans_to_average` (integer)
- `timestamp` (string)
- `units` (string): AU (absorbance, -log10 T) or % (transmittance)
- `valid_pixels` (integer): Pixels where the reference had enough unsaturated signal
- `values` (array): Downsampled values; None where invalid
- `warnings` (array)
- `wavelength_nm` (array)

### `measure_transmittance` (~191 tokens)

Measure Transmittance

Measure the transmittance spectrum %T = 100 (S - D) / (R - D) of the sample now in the
beam, using the stored dark and reference. Ask the user to insert the sample first. Also
returns values at `wavelengths_nm` and the deepest transmission dips.

Input parameters:

- `max_points` (integer): Maximum points returned (bin-averaged)
- `num_peaks` (integer): Number of peaks to report
- `save_path`: Optional new .csv file for the full-resolution data (existing files are not overwritten)
- `scans_to_average`: Spectra averaged (default: as the reference)
- `wavelength_max_nm`: Only report/search below this wavelength (nm)
- `wavelength_min_nm`: Only report/search above this wavelength (nm)
- `wavelengths_nm`: Wavelengths (nm) at which to report interpolated values

Output parameters:

- `at_wavelengths` (array)
- `dark_timestamp` (string)
- `integration_time_ms` (number)
- `kind` (string)
- `max_at_nm`
- `max_value`
- `peaks` (array): Absorbance maxima, or transmittance minima (dips)
- `pixels` (integer)
- `points_returned` (integer)
- `reference_timestamp` (string)
- `saved_to`
- `scans_to_average` (integer)
- `timestamp` (string)
- `units` (string): AU (absorbance, -log10 T) or % (transmittance)
- `valid_pixels` (integer): Pixels where the reference had enough unsaturated signal
- `values` (array): Downsampled values; None where invalid
- `warnings` (array)
- `wavelength_nm` (array)

### `find_peaks` (~152 tokens)

Find Peaks

Find peaks (or dips) with position, height, prominence and FWHM in the most recent
spectrum (intensity, absorbance or transmittance). Acquires a fresh intensity spectrum if
none has been taken yet.

Input parameters:

- `max_peaks` (integer): Maximum number of peaks
- `min_prominence_fraction` (number): Minimum prominence as a fraction of the data range
- `min_separation_nm` (number): Minimum distance between peaks, nm
- `mode` (string): Peaks (maxima) or dips (minima)
- `wavelength_max_nm`: Only report/search below this wavelength (nm)
- `wavelength_min_nm`: Only report/search above this wavelength (nm)

### `auto_integration_time` (~148 tokens)

Auto Integration Time

Adjust the integration time until the brightest raw pixel (optionally within a wavelength
window) is within the target band of saturation (default 70-85 %). Stays within the device
limits and the `max_integration_time_ms` safety limit. Re-take dark/reference afterwards.

Input parameters:

- `max_iterations` (integer): Maximum adjustment steps
- `target_max_percent` (number): Upper edge of the target band, % of saturation
- `target_min_percent` (number): Lower edge of the target band, % of saturation
- `wavelength_max_nm`: Only report/search below this wavelength (nm)
- `wavelength_min_nm`: Only report/search above this wavelength (nm)

### `read_detector_temperature` (~42 tokens)

Read Detector Temperature

Read the detector temperature from the thermo-electric cooler (TE-cooled models such as
the QE Pro, when seabreeze exposes the thermo_electric feature for them).

### `set_detector_cooling` (~97 tokens)

Set Detector Cooling

Enable the detector thermo-electric cooler at `setpoint_c` (TE-cooled models only). The
detector takes minutes to settle; dark current (and noise) drops as it cools. The TEC can only
cool to roughly 15-40 °C below ambient (QE Pro manual). Checked against `min_tec_setpoint_c`.

Input parameters:

- `setpoint_c` (number, required): Detector TEC setpoint, °C

### `detector_cooling_off` (~35 tokens)

Detector Cooling Off

Switch the detector thermo-electric cooler off (the detector warms to ambient). Does
nothing on spectrometers without a TEC.

## Diagnostics

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

## Score history

- 2026-09-30: 83
- 2026-09-29: 67
- 2026-09-28: 82
- 2026-09-27: 39
- 2026-09-26: 71

## Common questions

### What is the Ocean Insight Spectrometer MCP server?

Ocean Insight Spectrometer is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-ocean-spectrometer. MCP server for Ocean Insight / Ocean Optics spectrometers (python-seabreeze). This page covers its PyPI package (labmcp-ocean-spectrometer).

### Is the Ocean Insight Spectrometer MCP server safe to use?

Ocean Insight Spectrometer 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 Ocean Insight Spectrometer MCP server expose?

Ocean Insight Spectrometer exposes 16 tools: get_connection_info, get_command_log, reconnect, list_spectrometers, get_device_info, and 11 more. Their descriptions and schemas cost roughly 1,658 tokens of context every time the server is loaded.

### Is the Ocean Insight Spectrometer MCP server still maintained?

Ocean Insight Spectrometer 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 Ocean Insight Spectrometer MCP server under?

Ocean Insight Spectrometer 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-ocean-spectrometer/
- Socket report: https://socket.dev/pypi/package/labmcp-ocean-spectrometer
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/chemistry/ocean-spectrometer
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ocean-spectrometer/labmcp-ocean-spectrometer.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ocean-spectrometer/labmcp-ocean-spectrometer.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-ocean-spectrometer/labmcp-ocean-spectrometer