MCP Tools Directory
← Browse integrations

Developer tools

io.github.TheStevenJohnstone/ai-consensus

Free account · sign-in required

Contact io.github.TheStevenJohnstone/ai-consensus

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

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

Transport
stdio
Authentication
api-key
Initial setup
credentials
Runtime
unattended
Evidence
documented
Version
0.12.2
Package
ai-consensus-connector
Last compatibility test
Not independently tested

Connect your agent

ai-consensus-connector

Publisher README and npm manifest reviewed. Package and hosted service were not executed. The open-source connector is a client for a separate hosted deliberation service.

Capabilities: Request multi-model review, Start and retrieve asynchronous reviews, Check connection status and cancel runs

Connected profiles

Additional details

Registry identifier

io.github.TheStevenJohnstone/ai-consensus

Source ↗ · Checked 2026-09-17
Published version

0.12.2

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

npm

Source ↗ · Checked 2026-09-17
Required configuration names

AI_CONSENSUS_API_KEY

Source ↗ · Checked 2026-09-17
Source artifact

ai-consensus-connector

Source ↗ · Checked 2026-09-20
Source manifest version

0.12.2

Source ↗ · Checked 2026-09-20
Unattended configuration

The stdio connector can wait for a synchronous panel result or start a run and retrieve it later.

Source ↗ · Checked 2026-09-20
Authentication and prerequisites

Requires an AI Consensus API key associated with the user's hosted-service account and billing plan.

Source ↗ · Checked 2026-09-20
Connection configuration

A local MCP client runs npx -y ai-consensus-connector over stdio with AI_CONSENSUS_API_KEY; a self-hosted base URL is optional.

Source ↗ · Checked 2026-09-20
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-20