MCP.Market

Quinn's Conveyance — Paid ComfyUI Knowledge MCP server

online · 100% uptime
by jkomalleyjr·io.github.jkomalleyjr/quinns-conveyance·v0.1.0
No reviews yet

Paid ComfyUI knowledge tools. 5 tools $0.005 USDC/call on Base via x402; ping, list_topics free.

A91/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Quinn's Conveyance — Paid ComfyUI Knowledge MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Quinn's Conveyance — Paid ComfyUI Knowledge MCP tools (7)

write = sends, deletes, buys or posts
  • check_dead_endFree

    Check whether an approach to ComfyUI video generation is a known dead end before spending GPU time on it. Returns the failed approach, what was tested, and what to do instead. Use BEFORE running an experiment you're unsure about. Covers WanVideoWrapper, chaining, interpolation, and upscaling. Costs $0.005 per call, paid in USDC on Base via x402.

  • diagnose_comfyui_opsFree

    Fix ComfyUI operations issues on a remote Linux/DGX Spark host: process detection, restarts, port conflicts, SSH quirks. Use when ComfyUI is down, wedged, duplicated, or unreachable. Do NOT use for workflow/node errors — that's fix_comfyui_api_prompt_error. Costs $0.005 per call, paid in USDC on Base via x402.

  • fix_comfyui_api_prompt_errorFree

    Diagnose a ComfyUI API-prompt (/prompt) execution error and return the verified fix with corrected JSON. Use when a workflow submitted via the API fails at queue time with missing/invalid input errors or node type mismatches. Do NOT use for drag-and-drop UI workflow issues — API prompts only. Costs $0.005 per call, paid in USDC on Base via x402.

  • get_audiobook_recipeFree

    Get the verified pipeline recipes for long-form TTS audiobook production (Fish-Speech / VibeVoice) and lip-sync (LatentSync). Covers text prep, voice pipeline rules, and lip-sync config. Use when producing narrated audio or syncing dialogue to video. Costs $0.005 per call, paid in USDC on Base via x402.

  • get_chaining_ruleFree

    Get the verified rules for chaining AI video clips into a continuous sequence (MiniMax H3 / Wan). Covers true-last-frame chaining, crossfade vs hard cut decisions, and prompting for pace continuity. Use when assembling multi-clip sequences. Do NOT use for single-clip generation. Costs $0.005 per call, paid in USDC on Base via x402.

  • list_topicsFree

    List available paid knowledge tools and snippet IDs. Free — call this first to see what's covered.

  • pingFree

    Health check. Free.

Public scan report

scanner v0.1.10 · 2026-10-27 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 54ms20/20
  • Tool poisoning7 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Quinn's Conveyance — Paid ComfyUI Knowledge MCP compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 85% of 48,255 servers
Tools
7
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
310 ms
faster than 46% of 30,031 servers

What its tools let an agent do: 7 read

Install Quinn's Conveyance — Paid ComfyUI Knowledge MCP in Claude Code, Cursor or VS Code

claude mcp add --transport http quinns-conveyance https://demo.quinnsconveyance.com/mcp
Add to Cursor

What the publisher says

From the Quinn's Conveyance — Paid ComfyUI Knowledge MCP repository's README, as published. We do not edit it. Read it on GitHub

Quinn's Conveyance puts APIs behind HTTP 402 (the x402 protocol) so agents pay per call in USDC on Base — no API keys to issue, no signup forms, no cards, no invoicing, no billing stack to build. The wallet is the identity; the payment is the authorization.

This repo is the working proof: the live demo's source, and the SDK we ship to clients.

Live proof

  • Demo — an MCP server with 5 paid tools at $0.005/call: demo.quinnsconveyance.com
  • Insights — every challenge and settlement, public: demo.quinnsconveyance.com/insights
  • Settlement proof — a real mainnet payment, settled via Coinbase CDP: Basescan
  • Listings — Coinbase Bazaar + Agentic.market (all 5 tools), MCP Registry (io.github.jkomalleyjr/quinns-conveyance), PayAI Bazaar

The SDK — quinns-x402

The same code the demo runs, packaged. Paywall an Express API or an MCP server in minutes:

npm install quinns-x402
import { x402, createSettlementLogger } from "quinns-x402";

const logger = createSettlementLogger(process.env.DATABASE_URL!, { verify: true });

app.use(x402({
  payTo: "0xYourBaseWallet",               // settlements land here, directly
  price: "$0.005",
  resourceBaseUrl: "https://api.yourco.com",
  routes: { "GET /api/weather": { description: "Current weather for a city" } },
  onChallenge: logger.onChallenge,
  onSettlement: logger.onSettlement,
}));

What you get beyond the official @x402 packages:

  • Dual facilitators — Coinbase CDP (JWT auth) or PayAI, one config line
  • Discovery built in — Bazaar extension declared automatically; your endpoints index after their first paid call
  • A settlement ledger — every 402 challenge and settlement in Postgres: payer wallet, amount, latency, conversion funnel
  • Verification on every settlement — Flow Executor's 4 checks (signature, nonce, transfer log, validity window) recorded as verify_status, fail-open-but-loud, with a delayed re-check that corrects propagation-race false failures

Full docs: sdk/README.md · npm: quinns-x402

How the demo works

demo/server.ts — an Express + MCP (StreamableHTTP) server. Paid calls flow: 402 challenge → EIP-3009 signed authorization → facilitator settlement on Base → response. Settlements are logged to Postgres, verified, and rendered on the public Insights dashboard. Payments settle directly to the operator's wallet — the service never holds funds.

Services

Pilot program (3 slots): free implementation + 90 days of Operate Insights, in exchange for a logo, a quote, and a case study with real numbers. Terms: sales/pilot-agreement.md · sales/pilot-offer.md

Writing

  • I put an MCP server behind HTTP 402 — here's the exact setup
  • How We'll Measure the Agent Economy — the four-layer ruler we run: challenge→settlement funnel, wallet persistence, latency shape, verify_status on every settlement.

Principles

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Quinn's Conveyance — Paid ComfyUI Knowledge MCP: common questions

Is Quinn's Conveyance — Paid ComfyUI Knowledge MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Quinn's Conveyance — Paid ComfyUI Knowledge MCP safety report
How do I install Quinn's Conveyance — Paid ComfyUI Knowledge MCP?
It runs remotely at demo.quinnsconveyance.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Quinn's Conveyance — Paid ComfyUI Knowledge MCP need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Quinn's Conveyance — Paid ComfyUI Knowledge MCP maintained?
The last commit was 14 days ago (2026-10-21). The latest release is v0.1.0.
Is Quinn's Conveyance — Paid ComfyUI Knowledge MCP up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Quinn's Conveyance — Paid ComfyUI Knowledge MCP compare with other MCP servers?
safety score 91/100 (higher than 85% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.