# Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) (pypi · labmcp-ms-data)

MCP server for LC-MS data in mzML/mzMLb and Bruker timsTOF files; vendor formats via msconvert.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-ms-data`: 66/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-ms-data/labmcp-ms-data.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-ms-data/labmcp-ms-data)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-ms-data`
- Version: `0.1.1`
- 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**: 50/100
  - Malware scan not yet available for this package.
  - 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 23 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**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2374 tokens (~197/item across 12 items; 12 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**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% 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 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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 Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) runs locally as a PyPI package, launched with uvx labmcp-ms-data. 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-ms-data -- uvx labmcp-ms-data
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add k-dense-ai-labmcp-ms-data -- uvx labmcp-ms-data
```

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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.

### 2026-09-28 (score 66, +26)

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

### 2026-09-27 (score 40, −29)

- [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: 0.1.0 → 0.1.1

### 2026-09-26 (score 69)

First indexed and scored.

## MCP tools (12)

### `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_runs` (~151 tokens)

List Runs

Find mass-spectrometry runs in the data folder and detect each one's vendor and format
(mzML/mzML.gz/mzMLb, Bruker .d TDF or BAF, Agilent .d, Thermo .raw, Waters .raw folder,
SCIEX .wiff/.wiff2, Shimadzu .lcd, mzXML). `readable_directly=false` means the run must be
converted with convert_to_mzml before it can be analysed.

Input parameters:

- `max_results` (integer)
- `recursive` (boolean): Also search subfolders (up to 6 levels)
- `subfolder` (string): Folder to search, relative to the data folder

Output parameters:

- `data_folder` (string)
- `runs` (array)
- `simulated` (boolean)
- `total_found` (integer)
- `truncated` (boolean)

### `get_run_info` (~107 tokens)

Get Run Info

Describe one run: instrument vendor/model/serial (when the file records them), acquisition
date, software, number of spectra per MS level, retention-time and m/z ranges, polarity,
centroid/profile, and whether ion-mobility data is present. The first call on a large file
indexes it (can take a while); later calls are instant.

Input parameters:

- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run

Output parameters:

- `acquisition_date`
- `format` (string)
- `instrument_model`
- `instrument_serial`
- `instrument_vendor`
- `ion_mobility` (boolean)
- `mz_max`
- `mz_min`: Lowest observed (or acquisition-range) m/z
- `notes` (array)
- `path` (string)
- `polarity` (string)
- `rt_end_min`
- `rt_start_min`
- `sample_name`
- `simulated` (boolean)
- `software`
- `spectra_by_ms_level` (object)
- `spectra_total` (integer)
- `spectrum_type` (string)

### `get_tic` (~197 tokens)

Get Tic

Total ion chromatogram (sum of all intensities per spectrum vs retention time) for one MS
level, downsampled to `max_points` (keeping the maximum in each bin so peaks survive).
Returns the apex, median and area; `save_path` writes every point to CSV.

Input parameters:

- `max_points` (integer): Maximum points returned (downsampled, max per bin)
- `ms_level` (integer): MS level to use (1 = survey scans)
- `overwrite` (boolean): Allow replacing an existing save_path file
- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run
- `rt_end_min`: Only use spectra at or before this RT (min)
- `rt_start_min`: Only use spectra at or after this RT (min)
- `save_path`: Optional new .csv file inside the data folder for the full-resolution data

Output parameters:

- `area`: Trapezoidal integral over RT in minutes (intensity x min)
- `base_peak_mz`: BPC only: m/z of the base peak per point
- `intensity` (array)
- `kind` (string)
- `max_at_rt_min`
- `max_intensity`
- `median_intensity`
- `ms_level` (integer)
- `notes` (array)
- `path` (string)
- `points_returned` (integer)
- `rt_min` (array)
- `saved_to`
- `simulated` (boolean)
- `spectra_used` (integer)

### `get_bpc` (~201 tokens)

Get Bpc

Base peak chromatogram (intensity of the most intense peak per spectrum, with its m/z) vs
retention time, downsampled to `max_points`. Cleaner than the TIC for spotting eluting
compounds; the base-peak m/z tells you which ion dominates each part of the run.

Input parameters:

- `max_points` (integer): Maximum points returned (downsampled, max per bin)
- `ms_level` (integer): MS level to use (1 = survey scans)
- `overwrite` (boolean): Allow replacing an existing save_path file
- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run
- `rt_end_min`: Only use spectra at or before this RT (min)
- `rt_start_min`: Only use spectra at or after this RT (min)
- `save_path`: Optional new .csv file inside the data folder for the full-resolution data

Output parameters:

- `area`: Trapezoidal integral over RT in minutes (intensity x min)
- `base_peak_mz`: BPC only: m/z of the base peak per point
- `intensity` (array)
- `kind` (string)
- `max_at_rt_min`
- `max_intensity`
- `median_intensity`
- `ms_level` (integer)
- `notes` (array)
- `path` (string)
- `points_returned` (integer)
- `rt_min` (array)
- `saved_to`
- `simulated` (boolean)
- `spectra_used` (integer)

### `extract_ion_chromatogram` (~293 tokens)

Extract Ion Chromatogram

Extracted ion chromatogram (XIC/EIC) for one or more m/z values: the summed intensity
within ± tolerance (ppm or Da) in every MS1 spectrum (or another `ms_level`). For each target
returns the apex RT and intensity, the apex peak's boundaries, area (intensity x min, no
baseline subtraction) and FWHM, plus a downsampled trace. Reads every spectrum in the RT
window, so restrict `rt_start_min`/`rt_end_min` on long runs.

Input parameters:

- `max_points` (integer): Maximum points returned (downsampled, max per bin)
- `ms_level` (integer): MS level to use (1 = survey scans)
- `mz` (array, required): Target m/z value(s)
- `overwrite` (boolean): Allow replacing an existing save_path file
- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run
- `rt_end_min`: Only use spectra at or before this RT (min)
- `rt_start_min`: Only use spectra at or after this RT (min)
- `save_path`: Optional new .csv file inside the data folder for the full-resolution data
- `tolerance` (number): m/z tolerance (± this value)
- `tolerance_unit` (string): Tolerance unit: ppm or da

Output parameters:

- `ms_level` (integer)
- `path` (string)
- `rt_window_min`
- `saved_to`
- `simulated` (boolean)
- `spectra_used` (integer)
- `traces` (array)
- `warnings` (array)

### `get_spectrum` (~284 tokens)

Get Spectrum

Read one spectrum, chosen by `index`, `scan_number`, `native_id` or nearest `rt_min`
(give exactly one). Returns MS level, RT, polarity, centroid/profile, precursor m/z and
charge for MS2, a summary (peak count, TIC, base peak, m/z range) and the `top_n` most
intense peaks; `save_path` writes the full peak list to CSV. For profile spectra the top
peaks are local maxima of the profile.

Input parameters:

- `index`: 0-based spectrum index in the file
- `ms_level`: With rt_min: MS level to pick (default 1)
- `mz_max`: Only consider peaks below this m/z
- `mz_min`: Only consider peaks above this m/z
- `native_id`: Exact native spectrum id
- `overwrite` (boolean): Allow replacing an existing save_path file
- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run
- `rt_min`: Pick the spectrum nearest this RT (min)
- `save_path`: Optional new .csv file inside the data folder for the full-resolution data
- `scan_number`: Native scan number (e.g. Thermo scan=N)
- `top_n` (integer): Number of most intense peaks to return

Output parameters:

- `base_peak_intensity`
- `base_peak_mz`
- `filter_string`
- `index` (integer): 0-based position in the file
- `injection_time_ms`
- `ms_level` (integer)
- `mz_range`
- `native_id` (string)
- `notes` (array)
- `path` (string)
- `peak_count` (integer)
- `polarity` (string)
- `precursor`
- `rt_min`
- `saved_to`
- `scan_number`
- `simulated` (boolean)
- `spectrum_type` (string)
- `tic` (number): Sum of intensities (inside the m/z window, if given)
- `top_peaks` (array): Most intense peaks, highest first

### `find_ms2_scans` (~197 tokens)

Find Ms2 Scans

Find the MS2 (MSn) spectra whose precursor m/z is within ± tolerance of `precursor_mz`,
optionally within an RT window and for one charge state. Returns index, scan number, RT,
precursor m/z, error in ppm, charge and intensity; open any hit with get_spectrum.

Input parameters:

- `charge`: Only this precursor charge
- `max_results` (integer)
- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run
- `precursor_mz` (number, required): Precursor m/z to look for
- `rt_end_min`: Only use spectra at or before this RT (min)
- `rt_start_min`: Only use spectra at or after this RT (min)
- `tolerance` (number): m/z tolerance (± this value)
- `tolerance_unit` (string): Tolerance unit: ppm or da

Output parameters:

- `matches` (array)
- `path` (string)
- `precursor_mz` (number)
- `rt_window_min`
- `simulated` (boolean)
- `tolerance_da` (number)
- `total_matches` (integer)
- `truncated` (boolean)

### `summarise_run` (~96 tokens)

Summarise Run

Quick QC of a run: MS1/MS2 counts, TIC stability (CV, spray dropouts), where the signal
elutes, cycle time, MS2 scans per cycle, median injection times and how often MS2 hit the
maximum injection time, and precursor charge states. Returns plain-language warnings.

Input parameters:

- `path`: Run path relative to the data folder (from list_runs); may be omitted if there is one run

Output parameters:

- `median_cycle_time_s`: Median time between consecutive MS1 scans
- `median_ms1_injection_time_ms`
- `median_ms2_injection_time_ms`
- `ms1_spectra` (integer)
- `ms2_at_max_injection_time_percent`
- `ms2_per_cycle_max`
- `ms2_per_cycle_mean`
- `ms2_per_cycle_median`
- `ms2_precursor_charges` (object)
- `ms2_spectra` (integer)
- `msn_higher_spectra` (integer)
- `path` (string)
- `rt_end_min`
- `rt_start_min`
- `simulated` (boolean)
- `tic_cv_percent`: Coefficient of variation of the MS1 TIC (whole run)
- `tic_dropout_rts_min` (array)
- `tic_dropouts` (integer): MS1 scans with TIC < 20 % of the local median (spray instability)
- `tic_elution_quartiles_min`: RT at which 25 / 50 / 75 % of the summed MS1 TIC has eluted
- `tic_median`
- `warnings` (array)

### `convert_to_mzml` (~225 tokens)

Convert To Mzml

Convert a vendor file (Thermo .raw, Waters .raw, Agilent .d, SCIEX .wiff, Shimadzu .lcd,
Bruker .d) to mzML with the converter the user installed (ThermoRawFileParser, ProteoWizard
msconvert, or msconvert in Docker; chosen with --option converter=...). Writes a new file in
the data folder. Can take minutes; fails with install instructions if no converter is set up.

Input parameters:

- `dry_run` (boolean): Only show the command that would be run
- `gzip` (boolean): Write .mzML.gz
- `output_folder`: Folder for the .mzML, inside the data folder (default: next to the input)
- `overwrite` (boolean): Replace an existing output file
- `path` (string, required): Vendor file or folder (from list_runs), relative to the data folder
- `peak_picking` (boolean): Centroid with the vendor algorithm during conversion
- `timeout_s` (number): Give up after this many seconds

Output parameters:

- `command` (array)
- `converter` (string)
- `detected_format` (string)
- `dry_run` (boolean)
- `duration_s`
- `input` (string)
- `log_tail` (string)
- `notes` (array)
- `output` (string)
- `output_size_mb`
- `return_code`
- `success` (boolean)

## Diagnostics

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

## Score history

- 2026-09-30: 66
- 2026-09-29: 66
- 2026-09-28: 66
- 2026-09-27: 40
- 2026-09-26: 69

## Common questions

### What is the Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-ms-data. MCP server for LC-MS data in mzML/mzMLb and Bruker timsTOF files; vendor formats via msconvert. This page covers its PyPI package (labmcp-ms-data).

### Is the Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server safe to use?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) scores 66 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 Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server expose?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) exposes 12 tools: get_connection_info, get_command_log, reconnect, list_runs, get_run_info, and 7 more. Their descriptions and schemas cost roughly 1,872 tokens of context every time the server is loaded.

### Is the Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server still maintained?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) 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 Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) MCP server under?

Mass Spectrometry Data (mzML, Bruker TDF, vendor conversion) 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-ms-data/
- Socket report: https://socket.dev/pypi/package/labmcp-ms-data
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/chemistry/ms-data
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-data/labmcp-ms-data.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-data/labmcp-ms-data.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-data/labmcp-ms-data