# io.github.TheStevenJohnstone/ai-consensus (npm · ai-consensus-connector)

Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.

- Trust score: 65/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `ai-consensus-connector`: 65/100 (this document), [markdown](https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector.md), [page](https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector)

## Channel facts

- Registry: `npm`
- Package: `ai-consensus-connector`
- Version: `0.12.2`
- 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**: 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 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 288 tokens (~57/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 25% 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 thestevenjohnstone-ai-consensus -- npx -y ai-consensus-connector
```

### Codex

```bash
codex mcp add thestevenjohnstone-ai-consensus -- npx -y ai-consensus-connector
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add thestevenjohnstone-ai-consensus --command npx --arg -y --arg ai-consensus-connector
```

### Hermes

```yaml
mcp_servers:
  thestevenjohnstone-ai-consensus:
    command: "npx"
    args: ["-y", "ai-consensus-connector"]
```

### Other

```json
{
  "mcpServers": {
    "thestevenjohnstone-ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ]
    }
  }
}
```

## 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 65, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 61, +42)

- [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 regression] Tool coverage: 100 → unverified
- [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] Licence: MIT

### 2026-07-31 (score 19, −6)

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

### 2026-07-30 (score 25, 0)

- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 25, −18)

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

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (5)

### `consult_ai_consensus` (~133 tokens)

Route a decision, question, or task through three frontier AIs (Claude, GPT, Gemini) that answer independently, then cross-examine each other — returning one recommendation plus the strongest dissent. Intended as a STANDING part of the development loop: consult it as a matter of course for any decision of consequence (architecture, design, approach, tricky bugs, anything whose cost of being wrong is real) — not just rare emergencies. Purely mechanical edits do not need a run. A run takes a few minutes.

Input parameters:

- `prompt` (string, required): The decision, question, or task to run through AI Consensus.

### `start_ai_consensus` (~33 tokens)

Start an AI Consensus run without waiting; returns a run id to collect later.

Input parameters:

- `prompt` (string, required)

### `get_ai_consensus_result` (~31 tokens)

Fetch the status/result of an AI Consensus run by id.

Input parameters:

- `run_id` (string, required)

### `cancel_ai_consensus_run` (~29 tokens)

Cancel an in-progress AI Consensus run by id.

Input parameters:

- `run_id` (string, required)

### `check_ai_consensus_connection` (~62 tokens)

Zero-cost setup check: verifies the API is reachable, your AI Consensus key is accepted, and (on bring-your-own-keys plans) which provider keys are present. Does NOT start a deliberation and costs nothing. Use right after installing the connector.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 61
- 2026-08-01: 19
- 2026-07-31: 19
- 2026-07-30: 25
- 2026-07-28: 25
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/ai-consensus-connector
- Socket report: https://socket.dev/npm/package/ai-consensus-connector
- Repository: https://github.com/TheStevenJohnstone/ai-consensus-connector
- Website: https://ai-consensus.ai/
- Changelog RSS feed: https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector/changelog.json
- HTML version of this page: https://verifymcp.io/servers/thestevenjohnstone-ai-consensus/ai-consensus-connector