# LC-MS Worklist Builder (pypi · labmcp-ms-worklist)

MCP server that builds and validates LC-MS worklists for MassLynx, SCIEX OS, MassHunter, Xcalibur.

- Trust score: 81/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-ms-worklist`: 81/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-ms-worklist/labmcp-ms-worklist.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-ms-worklist/labmcp-ms-worklist)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-ms-worklist`
- 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**: 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1987 tokens (~165/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**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% 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 LC-MS Worklist Builder MCP server?

LC-MS Worklist Builder runs locally as a PyPI package, launched with uvx labmcp-ms-worklist. 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-worklist -- uvx labmcp-ms-worklist
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-29 (score 80, +10)

- [security improvement] Provenance: unverified → pass
- [security] The attested source repository moved: K-Dense-AI/lab-instrument-mcps

### 2026-09-28 (score 70, +31)

- [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, −30)

- [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_formats` (~86 tokens)

List Formats

List the supported import formats (Waters MassLynx, SCIEX OS, Agilent MassHunter, Thermo
Xcalibur): columns, required fields, sample-type names, file extensions, how to import, what
is verified against vendor documents and what is assumed, and the source URLs. Also lists the
position patterns and the formats that were researched but not implemented.

### `create_worklist` (~420 tokens)

Create Worklist

Create an in-memory draft worklist from a sample list plus defaults (methods, injection
volume, tray positions, data-file naming pattern). Nothing is written to disk until
export_worklist. Injection volumes above the max_injection_volume_ul limit are refused.

Input parameters:

- `bracket_type` (integer): Xcalibur only: 1 Overlapped, 2 None, 3 Non-Overlapped, 4 Open
- `data_file_pattern` (string): Data file naming pattern; placeholders {index} {sample_name} {sample_id} {type} {worklist} {date} {position}; illegal characters become '_'
- `data_path` (string): Data folder (Xcalibur Path column)
- `first_position` (string): If set, samples without a position get sequential positions from here, e.g. 'A1'
- `format` (string, required): Target vendor format (see list_formats)
- `injection_volume_ul`: Injection volume in µL for samples that don't set one
- `lc_method` (string): Default LC/inlet method (Waters INLET_FILE, SCIEX LC Method)
- `max_vial` (integer): Highest vial number (vial_number pattern)
- `ms_method` (string): Default MS/acquisition/instrument method
- `name` (string, required): Draft name (letters, digits, _ - .); used in file names
- `plate_size` (integer): Positions per plate/tray
- `position_pattern` (string): Autosampler position format to enforce
- `processing_method` (string): Default processing method (SCIEX OS, Xcalibur)
- `replace` (boolean): Replace an existing draft with the same name
- `samples` (array, required): Samples in run order: objects (sample_name required) or plain sample names
- `tune_file` (string): Default tune file (Waters MS_TUNE_FILE)
- `vendor_columns`: Constant vendor columns for every row, e.g. {'Rack Type': '...', 'Plate Type': '...'}

### `add_samples` (~79 tokens)

Add Samples

Append samples to a draft worklist (the worklist's defaults and automatic positions apply;
any blank/QC/randomisation plan is re-applied to the longer list with the same seed).

Input parameters:

- `name` (string, required): Draft worklist name
- `samples` (array, required): Samples in run order: objects (sample_name required) or plain sample names

### `insert_qc_blanks` (~319 tokens)

Insert Qc Blanks

Insert blanks and QC injections and optionally randomise the run order (with a recorded seed).
Replaces any previous plan, so calling it again does not duplicate blanks. The plan is
re-applied whenever samples are added; data-file names follow the new run order.

Input parameters:

- `blank_at_end` (boolean)
- `blank_at_start` (boolean)
- `blank_every_n`: Insert a blank after every N samples
- `blank_injection_volume_ul`: Injection volume in µL for samples that don't set one
- `blank_ms_method` (string): Method for blanks (default: the worklist's ms_method)
- `blank_name` (string)
- `blank_position` (string): Tray position of the blank vial
- `name` (string, required): Draft worklist name
- `qc_at_end` (integer): Number of QC injections at the end
- `qc_at_start` (integer): Number of QC injections at the start
- `qc_every_n`: Insert a QC after every N samples
- `qc_injection_volume_ul`: Injection volume in µL for samples that don't set one
- `qc_name` (string)
- `qc_position` (string): Tray position of the pooled QC vial
- `randomize` (boolean): Randomise the run order of the samples first
- `randomize_types` (array): Which sample types are shuffled among their own slots (standards stay put by default)
- `seed`: Random seed (a new one is drawn and recorded if omitted)

### `get_worklist` (~59 tokens)

Get Worklist

Show a draft worklist in run order, with its defaults, blank/QC plan, randomisation seed and
the history of operations applied to it.

Input parameters:

- `max_rows` (integer)
- `name` (string, required): Draft worklist name

### `list_worklists` (~24 tokens)

List Worklists

List the draft worklists in memory and the files in the output folder.

### `validate_worklist` (~98 tokens)

Validate Worklist

Check a draft against the target format: required fields, duplicate data-file names,
characters Windows does not allow in file names, tray/vial position format and plate bounds,
injection volume (> 0 and <= the max_injection_volume_ul limit), and method file extensions.
Errors block export; warnings don't.

Input parameters:

- `format`: Validate for another vendor format (default: the draft's)
- `name` (string, required): Draft worklist name

Output parameters:

- `errors` (array)
- `format` (string)
- `sample_count` (integer)
- `valid` (boolean): True when there are no errors (warnings are allowed)
- `warnings` (array)
- `worklist` (string)

### `export_worklist` (~260 tokens)

Export Worklist

Validate the draft and write the vendor import file into the output folder. Returns the path,
a preview of the first lines, warnings and import instructions. Refuses if validation finds
errors or the file exists (unless overwrite=true). This does not start an acquisition: a person
imports the file into the acquisition software.

Input parameters:

- `bracket_type`: Xcalibur bracket type override
- `delimiter`: Field separator (Xcalibur must match the Windows list separator)
- `filename`: File name inside the output folder (default '<name>_<format>.csv')
- `format`: Vendor format (default: the draft's); use another to convert
- `name` (string, required): Draft worklist name
- `overwrite` (boolean): Replace an existing file of the same name
- `template_columns`: Header columns to use instead of a template file
- `template_path`: A blank batch/sequence/worklist exported from the vendor software, in the output folder; its header (and delimiter) is used
- `utf8_bom`: Force a UTF-8 BOM on/off (default per format)
- `write_provenance` (boolean): Also write <file>.provenance.json (history, seed, original sample order)

### `import_worklist` (~118 tokens)

Import Worklist

Parse an existing MassLynx, SCIEX OS, MassHunter or Xcalibur import file from the output
folder into a draft, so it can be validated, edited or exported in another vendor's format.
Columns without a neutral equivalent are kept verbatim. Only reads; nothing is written.

Input parameters:

- `format`: Format; detected from the header if omitted
- `name`: Draft name (default: the file name)
- `path` (string, required): File in the output folder (relative path)
- `replace` (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-worklist/labmcp-ms-worklist#diagnostics

## Score history

- 2026-09-30: 81
- 2026-09-29: 80
- 2026-09-28: 70
- 2026-09-27: 39
- 2026-09-26: 69

## Common questions

### What is the LC-MS Worklist Builder MCP server?

LC-MS Worklist Builder is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-ms-worklist. MCP server that builds and validates LC-MS worklists for MassLynx, SCIEX OS, MassHunter, Xcalibur. This page covers its PyPI package (labmcp-ms-worklist).

### Is the LC-MS Worklist Builder MCP server safe to use?

LC-MS Worklist Builder scores 81 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 LC-MS Worklist Builder MCP server expose?

LC-MS Worklist Builder exposes 12 tools: get_connection_info, get_command_log, reconnect, list_formats, create_worklist, and 7 more. Their descriptions and schemas cost roughly 1,584 tokens of context every time the server is loaded.

### Is the LC-MS Worklist Builder MCP server still maintained?

LC-MS Worklist Builder 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 LC-MS Worklist Builder MCP server under?

LC-MS Worklist Builder 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-worklist/
- Socket report: https://socket.dev/pypi/package/labmcp-ms-worklist
- 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-worklist
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-worklist/labmcp-ms-worklist.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-worklist/labmcp-ms-worklist.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-ms-worklist/labmcp-ms-worklist