Market evidence with receipts: every claim resolves to a real stored record you can fetch back.
MCPpedia last refreshed this data
io.github.Godzilla-lab/quorum is an MCP server that market evidence with receipts: every claim resolves to a real stored record you can fetch back. Its tool list has not been published yet over http, requires no API key, and scores 82/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"io-github-godzilla-lab-quorum": {
"args": [
"-y",
"quorum"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Market evidence with receipts: every claim resolves to a real stored record you can fetch back.
Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.
npx -y 'quorum' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked quorum against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in other
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
SQL for Android APK and DEX files: classes, methods, strings, references and smali.
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
MCP Security Weekly
Get CVE alerts and security updates for io.github.Godzilla-lab/quorum and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Market evidence with receipts.
Give it a subject, get back what a market actually says. Every claim carries receipt ids, and every receipt id resolves to a real stored record you can fetch back. Fabricated citations are structurally impossible, and a test proves it rather than a README asserting it.
[!TIP] The interesting part is not that it finds evidence. It is that you can check it. Every id in every answer resolves through
GET /v1/evidence/{id}, andPOST /v1/verifywill re-resolve a set of claims against the corpus, ours or anybody else's. An id that does not resolve is a claim that was never real.
{
"finding": "Sizing runs small, and buyers only discover it after delivery",
"corroboration": { "records": 31, "channels": 5 },
"receipts": ["rc_8f2a1", "rc_44b0e", "rc_91c37"],
"confidence": "finding"
}
GET /v1/evidence/rc_8f2a1 returns the actual comment, its score, where it was
posted, when, and its permalink. A customer of your customer can click a claim
and read the human who said it.
The hosted API lives at https://quorum-api-j15n.onrender.com, on a free tier instance that sleeps when idle, so the first request after a quiet spell waits a few seconds for it to wake.
The hosted instance is keyed while the API is early. The API root says how to request a key, and always says which mode the instance you are talking to is in. The health endpoint needs no key, so you can check it is alive right now:
curl https://quorum-api-j15n.onrender.com/v1/healthz
Self hosting supports open mode or per key auth, quotas, tenancy and webhook
secrets, all self served from GET /v1/usage.
[!NOTE] On Windows, the curl bundled with Git Bash uses the Schannel TLS stack, which refuses any HTTPS connection when it cannot reach the certificate revocation servers (
CRYPT_E_REVOCATION_OFFLINE, common behind corporate proxies and VPNs). That is the network, not this API. Add--ssl-revoke-best-effortto the curl command, or call from WSL or PowerShell instead.
Voice of customer from public archives, competitor ads ranked by how long they have actually been running, and a video versus static verdict computed as arithmetic rather than opinion. It keeps everything it reads, so the second question about a market is nearly free and the archive can be asked about the past.
Key capabilities