io. github. Godzilla-lab/ quorum
by Godzilla-lab · remote · no sign-in to list tools · v0.1.0 · published by GitHub user Godzilla-lab
Market evidence with receipts: every claim resolves to a real stored record you can fetch back.
5 tools: 2 change things and 3 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things2Claude Code: ask: see these tools
- Only reads3Claude Code: allow: see these tools
1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http quorum https://quorum-api-j15n.onrender.com/mcpFindings
Matches of fixed checks, with the text they matched.
- Warnget_receipt
The input schema at properties.receiptIds.description contains "any other tool", wording about other tools or servers.
What this check looks forMatched text
inputSchema.properties.receiptIds.description: "Receipt ids, as returned by any other tool. Up to 50."
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
5 tools
Changes things 2Claude Code: ask
category_warmthHow much is already held for a category, and therefore whether asking about it is instant and free or slow and expensive.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it How much is already held for a category, and therefore whether asking about it is instant and free or slow and expensive. Check this BEFORE starting a report. With no category it lists what is held, so orient here instead of guessing slugs.
Annotations the server declares
- title: Check category warmth
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
research_productStart collecting evidence on a product or topic from public sources.No findings
Why it is in this group
- The description's first verb is "start": a word for a change.
Description, as the server wrote it Start collecting evidence on a product or topic from public sources. RETURNS AT ONCE: the harvest runs in the background, the first records land within a minute, and a full run takes minutes. Then call `search_evidence` or `category_warmth` for the same subject after about 30 seconds and keep calling while the counts grow; stop when they stop. Every receipt returned along the way is already a real record. Calling this twice for one subject joins the same run rather than starting another.
Annotations the server declares
- title: Start a harvest
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 3Claude Code: allow
compare_formatsVideo versus static advertising for a category, computed from how long real ads actually ran rather than from opinion.No findings
Why it is in this group
- The name "compare_formats" says "compare": a word for reading.
Description, as the server wrote it Video versus static advertising for a category, computed from how long real ads actually ran rather than from opinion. Returns a verdict, its confidence, and the ads behind it.
Annotations the server declares
- title: Compare ad formats
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_receiptResolve receipt ids to the real records behind them.1 finding
Why it is in this group
- The name "get_receipt" says "get": a word for reading.
Findings
- Warn
The input schema at properties.receiptIds.description contains "any other tool", wording about other tools or servers.
What this check looks forMatched text
inputSchema.properties.receiptIds.description: "Receipt ids, as returned by any other tool. Up to 50."
Description, as the server wrote it Resolve receipt ids to the real records behind them. This is how you CHECK a claim: if an id does not resolve, the claim citing it was not real. Takes one id or many. Long records are truncated with notice; pass full: true for complete text.
Annotations the server declares
- title: Resolve receipt ids
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_evidenceSearch the retained corpus for what people actually said about a product or topic.No findings
Why it is in this group
- The name "search_evidence" says "search": a word for reading.
Description, as the server wrote it Search the retained corpus for what people actually said about a product or topic. Returns how many independent records exist, across how many channels, whether that clears the corroboration threshold, and the loudest few quotes with their receipt ids. Costs nothing and touches no network.
Annotations the server declares
- title: Search the evidence corpus
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http quorum https://quorum-api-j15n.onrender.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__quorum__search_evidence",
"mcp__quorum__get_receipt",
"mcp__quorum__compare_formats"
],
"ask": [
"mcp__quorum__research_product",
"mcp__quorum__category_warmth"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as quorum. Review it before you use it.
