# io.github.nickjlamb/studydiff (npm · studydiff-mcp)

Explain why two scientific papers disagree, every claim grounded in a verbatim source quote.

- Trust score: 68/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `studydiff-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/nickjlamb-studydiff/studydiff-mcp.md), [page](https://verifymcp.io/servers/nickjlamb-studydiff/studydiff-mcp)

## Channel facts

- Registry: `npm`
- Package: `studydiff-mcp`
- Version: `0.2.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - 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 20 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 414 tokens (~138/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add nickjlamb-studydiff -- npx -y studydiff-mcp
```

### Codex

```bash
codex mcp add nickjlamb-studydiff -- npx -y studydiff-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add nickjlamb-studydiff --command npx --arg -y --arg studydiff-mcp
```

### Hermes

```yaml
mcp_servers:
  nickjlamb-studydiff:
    command: "npx"
    args: ["-y", "studydiff-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "nickjlamb-studydiff": {
      "command": "npx",
      "args": [
        "-y",
        "studydiff-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 68, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 64, +59)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 5, −1)

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

### 2026-07-31 (score 6, −40)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (3)

### `compare_studies` (~228 tokens)

Compare two studies and explain why they disagree

Explain WHY two scientific papers reach different conclusions. Extracts each study design (species, model, intervention, assay, dose, timing, endpoint, sample size, statistic, finding, limitations), verifies every extracted value against the source text with deterministic grounding, then ranks the design differences that most plausibly drive the disagreement (primary driver / also differs / ruled out) and suggests what evidence would resolve it. Every claim is traced to a verbatim quote; unsupported fields are returned as "not reported" rather than guessed. Never picks a winner. Each paper is given as {id} (PMID or DOI) or {text}. Requires ANTHROPIC_API_KEY – use compare_example for a no-key demonstration.

Input parameters:

- `paperA` (object, required): First study – {id} (PMID/DOI) or {citation, text}
- `paperB` (object, required): Second study – {id} (PMID/DOI) or {citation, text}
- `question` (string): The question under comparison, e.g. "Is the Treg lineage stable in vivo?"

### `compare_example` (~154 tokens)

Run a cached worked example

Run one of StudyDiff's built-in worked examples – real, famous contradictions with verbatim abstracts. Runs fully offline against cached papers: no API key and no network needed, so it is the quickest way to see the grounded output. Options: "mouse-inflammation" (Seok 2013 vs Takao 2015 – same datasets, opposite conclusions), "resveratrol-sirt1" (Howitz 2003 vs Beher 2009 – an assay artifact), "treg-stability" (Zhou 2009 vs Rubtsov 2010 – stable vs unstable Treg lineage, driven by the fate-mapping method).

Input parameters:

- `example` (string, required): Which built-in example to run

### `list_examples` (~32 tokens)

List the built-in worked examples

List StudyDiff's cached worked examples (real published contradictions) that can be run with compare_example without an API key.

## Diagnostics

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

## Score history

- 2026-08-03: 68
- 2026-08-02: 64
- 2026-08-01: 5
- 2026-07-31: 6
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

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