# io.github.nickjlamb/groundwork (npm · @pharmatools/groundwork)

Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.

- Trust score: 85/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@pharmatools/groundwork`: 85/100 (this document), [markdown](https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork.md), [page](https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork)

## Channel facts

- Registry: `npm`
- Package: `@pharmatools/groundwork`
- Version: `0.4.1`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 37 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 735 tokens (~147/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.nickjlamb/groundwork MCP server?

io.github.nickjlamb/groundwork runs locally as an npm package, launched with npx -y @pharmatools/groundwork. 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 nickjlamb-groundwork -- npx -y @pharmatools/groundwork
```

### Cursor

```json
{
  "mcpServers": {
    "nickjlamb-groundwork": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/groundwork"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nickjlamb-groundwork": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/groundwork"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add nickjlamb-groundwork -- npx -y @pharmatools/groundwork
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nickjlamb-groundwork": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pharmatools/groundwork"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nickjlamb-groundwork --command npx --arg -y --arg @pharmatools/groundwork
```

### Hermes

```yaml
mcp_servers:
  nickjlamb-groundwork:
    command: "npx"
    args: ["-y", "@pharmatools/groundwork"]
```

### Netclaw

```json
{
  "McpServers": {
    "nickjlamb-groundwork": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pharmatools/groundwork"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add nickjlamb-groundwork -t stdio -c npx -a -y @pharmatools/groundwork
```

### Other

```json
{
  "mcpServers": {
    "nickjlamb-groundwork": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/groundwork"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 84, −1)

- [functional] Stability: pass → 0.90

### 2026-10-28 (score 85, 0)

- [security] Stability: 0.97 → pass

### 2026-10-27 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `check_answer_grounding` (~202 tokens)

Check one answer's grounding

Deterministically check a single answer against the context it should be grounded in: required facts (anchors) present, every number traceable to the context, abstention when the question is unanswerable. Same logic as the CI gate — no model, no network. Returns pass/fail with named issues.

Input parameters:

- `abstain_markers` (array): Phrases that count as a valid refusal (defaults cover common forms)
- `allowed_new_numbers` (array): Numbers legitimately absent from the context (e.g. computed totals)
- `answer` (string, required): The answer to check
- `answer_anchors` (array): Facts a correct answer MUST contain (with acceptable rephrasings)
- `answerable` (boolean): false → the context cannot answer this; the only correct behaviour is abstention
- `context` (string, required): The retrieved passage(s) the answer must be grounded in
- `question` (string, required): The question that was asked

### `check_extraction` (~221 tokens)

Check one extracted record

Deterministically check a structured extraction against its hand-labelled gold record: schema validity (nullable fields are the abstention contract), field accuracy with per-field normalisers (dates → ISO, money → minor units) and aliases, and fabrication — a non-null value in a field whose gold is null (a guessed date of birth the document never stated). Same logic as the CI gate — no model, no network. Returns pass/fail with named issues and a per-field verdict.

Input parameters:

- `aliases` (object): Per-field acceptable alternative gold values (matched after normalisation)
- `gold` (object, required): The hand-labelled gold record; null means THE DOCUMENT DOES NOT STATE IT — gold's keys define which fields are compared
- `normalize` (object): Per-field normaliser applied to both sides before comparing
- `record` (object, required): The record the system extracted ({ field: value | null })
- `schema` (object): The JSON Schema the record must validate against (type a must-find field non-nullable, a may-be-absent field nullable)

### `check_readiness` (~127 tokens)

Run the readiness gate on a repo

Run `groundwork check` in a repo that has a scaffolded harness: redaction self-test, then the archetype's eval (grounding for document-qa, extraction for extraction) against the repo's own gold set. Returns the exit code, the main scorer's metrics, and any named failures — exactly what CI would report.

Input parameters:

- `baseline` (boolean): Freeze this run as the regression floor
- `ci` (boolean): Also compare against the committed baseline and fail on regression
- `dir` (string, required): Absolute path to the repo root (the directory containing groundwork/)

### `scaffold_harness` (~128 tokens)

Scaffold the readiness harness into a repo

Run `groundwork init [archetype]` in a repo: writes the adapter boundary, redaction config, gold-set templates, GitHub Action, and playbook for a deployment pattern — document-qa (documents → grounded answers) or extraction (documents → structured fields). Never overwrites existing files. After scaffolding, the human wires groundwork/adapter.mjs and replaces the example gold cases with real ones.

Input parameters:

- `archetype` (string): Deployment pattern to scaffold (default: document-qa)
- `dir` (string, required): Absolute path to the repo root to scaffold into

### `cost_summary` (~57 tokens)

Summarise measured token costs

Run `groundwork cost` in a repo: measured token usage from eval runs, with savings recommendations in leverage order (prompt caching, batching, context trimming, model routing last).

Input parameters:

- `dir` (string, required): Absolute path to the repo root

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork#diagnostics

## Score history

- 2026-11-05: 85
- 2026-11-04: 84
- 2026-11-03: 84
- 2026-11-02: 85
- 2026-11-01: 85
- 2026-10-31: 85
- 2026-10-30: 85
- 2026-10-29: 85
- 2026-10-28: 85
- 2026-10-27: 85
- 2026-10-26: 84
- 2026-10-25: 84
- 2026-10-24: 83
- 2026-10-23: 83
- 2026-10-22: 82
- 2026-10-21: 82
- 2026-10-20: 81
- 2026-10-19: 81
- 2026-10-18: 80
- 2026-10-17: 80
- 2026-10-16: 79
- 2026-10-15: 79
- 2026-10-14: 78
- 2026-10-13: 78
- 2026-10-12: 78
- 2026-10-11: 76
- 2026-10-07: 75
- 2026-10-06: 71
- 2026-10-05: 71
- 2026-10-04: 71

## Common questions

### What is the io.github.nickjlamb/groundwork MCP server?

io.github.nickjlamb/groundwork is an MCP server listed in the public MCP registry as io.github.nickjlamb/groundwork. Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate. This page covers its npm package (@pharmatools/groundwork).

### Is the io.github.nickjlamb/groundwork MCP server safe to use?

io.github.nickjlamb/groundwork scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 io.github.nickjlamb/groundwork MCP server expose?

io.github.nickjlamb/groundwork exposes 5 tools: check_answer_grounding, check_extraction, check_readiness, scaffold_harness, cost_summary. Their descriptions and schemas cost roughly 735 tokens of context every time the server is loaded.

### Is the io.github.nickjlamb/groundwork MCP server still maintained?

io.github.nickjlamb/groundwork is still listed as active in the MCP registry. We last reached this channel on 5 November 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 io.github.nickjlamb/groundwork MCP server under?

io.github.nickjlamb/groundwork declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@pharmatools/groundwork
- Socket report: https://socket.dev/npm/package/@pharmatools/groundwork
- Repository: https://github.com/nickjlamb/groundwork
- Changelog RSS feed: https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork.xml
- Changelog JSON feed: https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork.json
- HTML version of this page: https://verifymcp.io/servers/nickjlamb-groundwork/pharmatools-groundwork