Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.TheStevenJohnstone/ai-consensus

NPM · AI-CONSENSUS-CONNECTOR · SCANNED AUG 3

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

+22 this week 65 Trust /100
Trust breakdown (6 categories)

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. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 288 tokens (~57/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 25% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · ai-consensus-connector

# add to Claude Code
claude mcp add thestevenjohnstone-ai-consensus -- npx -y ai-consensus-connector
# add to Codex CLI
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
    }
  }
}
# add to OpenClaw
openclaw mcp add thestevenjohnstone-ai-consensus --command npx --arg -y --arg ai-consensus-connector
# ~/.hermes/config.yaml
mcp_servers:
  thestevenjohnstone-ai-consensus:
    command: "npx"
    args: ["-y", "ai-consensus-connector"]
// mcp.json
{
  "mcpServers": {
    "thestevenjohnstone-ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +42
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: 100 → unverified functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → good functional
    • Licence: MIT functional
  • 31 Jul 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • Malware scan: pass → unverified security
    • Dependency health: partial → unverified functional
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −18
    • Tool coverage: 100 → unverified functional
    • Dependency health: unverified → partial functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 43

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~288 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
cancel_ai_consensus_run ~29

Cancel an in-progress AI Consensus run by id.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

check_ai_consensus_connection ~62

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

consult_ai_consensus ~133

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.

NameTypeReqDescription
promptstringyesThe decision, question, or task to run through AI Consensus.

No output schema declared.

No examples provided.

get_ai_consensus_result ~31

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

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

start_ai_consensus ~33

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

NameTypeReqDescription
promptstringyes

No output schema declared.

No examples provided.