# io.github.nickjlamb/opengate-mcp (npm · @pharmatools/opengate-mcp)

Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

- Trust score: 75/100 (medium)
- Change this week: +30
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@pharmatools/opengate-mcp`: 75/100 (this document), [markdown](https://verifymcp.io/servers/nickjlamb-opengate-mcp/pharmatools-opengate-mcp.md), [page](https://verifymcp.io/servers/nickjlamb-opengate-mcp/pharmatools-opengate-mcp)

## Channel facts

- Registry: `npm`
- Package: `@pharmatools/opengate-mcp`
- Version: `0.1.4`
- 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 (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to nickjlamb/opengate).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 27 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 232 tokens (~232/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add nickjlamb-opengate-mcp -- npx -y @pharmatools/opengate-mcp
```

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "nickjlamb-opengate-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/opengate-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.

### 2026-08-02 (score 75, +70)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [security] The attested source repository moved: nickjlamb/opengate
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 5, −15)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 20, −4)

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

### 2026-07-28 (score 24, −21)

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

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (1)

### `check_grounding` (~232 tokens)

Check whether an answer is grounded in the provided context. Deterministic (no LLM judge): verifies that required facts appear in the answer, that every number in the answer traces to the context, and — for questions the context cannot answer — that the answer abstains instead of fabricating. Use this to self-check RAG / document-QA / retrieval answers before returning them.

Input parameters:

- `allowed_new_numbers` (array): Numbers the answer may introduce that are not in the context (e.g. from the question).
- `answer` (string, required): The answer to check.
- `context` (required): The retrieved context the answer must be grounded in (a string, or an array of passages).
- `expected_facts` (array): Facts a correct answer must contain (e.g. "30 days", "no restocking fee"). Each must appear in the answer.
- `must_abstain` (boolean): Set true when the context does NOT contain the answer: the answer must then decline rather than fabricate.
- `question` (string): The original question (optional; lets numbers from the question count as grounded).

## Diagnostics

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

## Score history

- 2026-08-03: 75
- 2026-08-02: 75
- 2026-08-01: 5
- 2026-07-31: 20
- 2026-07-30: 24
- 2026-07-28: 24
- 2026-07-27: 45

## Links

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