Quorum with Cursor.

Wiring it up

Quorum is a hosted MCP server. There is no package to install and nothing runs on your machine.

.cursor/mcp.json  (project)  ·  ~/.cursor/mcp.json  (global)

{
  "mcpServers": {
    "quorum": {
      "type": "http",
      "url": "https://www.quorum.dog/mcp",
      "headers": { "Authorization": "Bearer ${env:QUORUM_API_KEY}" }
    }
  }
}

Cursor interpolates ${env:...} in both url and headers, so the key can live in your environment rather than in a file you commit.

"type": "http" was missing from this block while the other two guides carried it. Cursor will infer a remote server from url alone, so the shorter form worked — but three configs for one server that differ in ways nothing explains is how a reader concludes the difference is meaningful and copies it somewhere it is not. All three now state the transport.

Get a key from your organisation dashboard.

What you get

All six are on the hosted server. The two testing tools spend real money on purpose — run_test bills per question at 25% off normal deliberate pricing and takes dry_run: true to price a run without spending anything; certify_mode commits $50 flat for 150 questions and runs for roughly two and a half hours, because the shared execution engine paces at about one question a minute. Do not call either speculatively.

estimate is worth more than its price row suggests. Alongside difficulty_score and task_type it returns deliberation_value — whether a panel is expected to help here, not just what it would cost. likely_helps on multi-step reasoning, likely_hurts when the answer is a passage to be reproduced rather than reasoned to (a synthesis pass rewrites by design, which corrupts it), unknown when there is no strong signal either way. It carries basis: "hypothesis" and its evidence line — LiveBench 2026-08-22, n=36, plus tier — so you can tell advice from measurement. The escalation router shows it in a branch.

One Cursor behaviour worth knowing

What it is good for here

Cursor's agent has your repository; Quorum has whatever paragraph you hand it. That shapes the pairing.

• Decisions you cannot cheaply reverse — anything with a migration behind it. Differently-trained models genuinely disagree here, and a confidently-wrong single answer is expensive.
• Attacking an answer you already have. Hand the proposed approach to the panel and ask what breaks. The useful output is often the disagreement, not the synthesis.
• Not for mechanical edits or tight iteration loops. A 28-second call costs more rhythm than a wrong rename costs time.

The paper

This page gets Quorum wired into Cursor. AI Deliberation & Cursor is the other half: when convening a panel here is worth the wait, the jobs it pays off on, and the ones it does not, with the exhibits behind each. 14 pages, PDF.

Every paper in the series sits on the whitepaper shelf.

Check it works

Ask your assistant to call list_modes. It is free, it requires a valid key, and it returns the panels you are actually entitled to — so one real answer proves the URL, the key and the wiring together.

curl -sS -X POST https://www.quorum.dog/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer qk_..." \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

A GET to that URL returns 405. That is correct, not a fault — the server is stateless, so there is nothing for a GET to stream.

Before you put it in a loop

Measured on production, 2026-08-20:

Asking what a question is costs effectively nothing. Convening the panel does not. The escalation router covers how to decide between them — and the decision is yours to make, not a threshold we set.

Other editors

Claude Code and Cursor nest servers under mcpServers. VS Code uses servers. Same protocol, same URL, different wrapper key — and the wrong one fails silently rather than telling you why.