AI Consensus runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 21 Jul 2026.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Today is the operative word: we check AI Consensus every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ai-consensus -- npx -y ai-consensus-connector
{
"mcpServers": {
"ai-consensus": {
"args": [
"-y",
"ai-consensus-connector"
],
"command": "npx"
}
}
}
[mcp_servers.ai-consensus]
command = "npx"
args = ["-y", "ai-consensus-connector"]
{
"mcpServers": {
"ai-consensus": {
"args": [
"-y",
"ai-consensus-connector"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ai-consensus": {
"args": [
"-y",
"ai-consensus-connector"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AI_CONSENSUS_API_KEY (AI Consensus API key (create one at https://ai-consensus.ai/app/api-keys)).
The author declared them in the registry entry; get the values from the project itself.
Multi-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning
Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.
Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.
Deterministic release gate for AI-written code and coding agents.
Live status, API pricing and rate limits for ChatGPT, Claude, Gemini, Cursor and 42+ AI tools.
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
Memi is the read-only design engineering audit and skill layer for coding agents.
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Answers built from our own checks of this server.