marketnow-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@marketnow-mcpCheck revocation status and fingerprint the tool surface of this MCP server"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Universal Trust Adapter (UTA)
The USB-C of agent trust.
UTA translates between ALL trust credential formats used by AI agents via a canonical Universal Trust Schema (UTS).
Like Zapier connects applications, UTA connects trust standards.
Built by Edison Flores & Alejandro Flores at AliceLabs LLC (Wyoming, USA).
⚡ Verify our claims — the stranger test (30 seconds)
Every trust claim in this repo is re-derivable by a stranger, from live public URLs, with no account and no trust in our endpoints:
# 9 checks against Sigstore Rekor's LIVE transparency-log data:
# entry exists · content hash · countersignature · signed tree head ·
# Merkle inclusion proof · C2SP checkpoint — all verified locally.
curl -sL https://www.marketnow.site/uta/conformance/anchors/verify-rekor.mjs -o verify-rekor.mjs
node verify-rekor.mjs
# Full conformance suite (14 vectors, stage scoring, curl + node only):
# https://www.marketnow.site/uta/conformance/Exercised in production, receipts public: we rotated our CA key mn-ca-002 → mn-ca-003 on 2026-09-08 under suspected compromise (no confirmed leak). Revocation published same-day. Three Rekor log entries (logIndex 2762061972, 2764017355, 2764479676) anchor the digests, and the published npm tarball's tar layer rebuilds byte-exact from source (sha256 519d406a…).
Related MCP server: io.github.yugantm/hvtracker-mcp
🌐 The Stranger Manifesto — 13 languages
Trust that requires membership is not trust. It's a guest list.
Ten build rules for stranger-verifiable agent trust — read it in your language (every version anchored to the same live receipts):
English · Español · Português · Français · Deutsch · Italiano · Русский · 日本語 · 中文 · 한국어 · हिन्दी · العربية · Türkçe
Markdown sources: manifesto/ — one file per language, same content, same receipts.
Rendered right here on GitHub; the marketnow.site/manifesto/ pages ship with the next site deploy.
🌍 Visa & Mastercard article — 14 languages
"Visa has a Trusted Agent Protocol. Mastercard has Verifiable Intent. Here's the layer neither one gives you."
🌍 Global Trust Series (multi-language, 2026-09-08)
The 2026 gray-market quota trust crisis, documented — plus the receipts-based fix:
English — You Paid an AI Reseller — Then the Rules Changed Mid-Cycle
中文 — 你买的 AI 合租/中转被改规则或跑路?开发者自保清单
Русский — Оплатили AI-подписку через посредника — а правила изменились посреди цикла?
Español — Pagaste por Claude o Cursor a un revendedor ¿y las reglas cambiaron a mitad del ciclo?
Sourced timeline (EN) — The 2026 AI Quota Gray-Market Trust Crisis — A Sourced Timeline
Series index · Verify a trust card: https://marketnow.site/verify
🆕 What's new — v5.1 (revocation that answers + tool fingerprinting)
Release v5.1 — roadmap items 1 & 5 (commit 7fb7db6a, Rekor anchor #4):
ATC Revocation + Transparency Log (MNR-CRL-1.0) — a signed, append-only revocation registry for Agent Trust Cards and CA keys. The
/api/trust?action=revocationpage used to promise an OCSP responder that returned 404; nowGET /api/ocsp?card_id=…/?kid=…answers for real: VALID / EXPIRED / REVOKED / SUPERSEDED / UNKNOWN, with PERMIT/DENY recommendation, fail-closed semantics, and the CRL signature embedded so any client can verify the signed layer independently (GET /api/crl). Seeded with real events — 3 superseded ATCs + themn-ca-002key compromise (2026-09-08).Cryptographic Tool Fingerprinting (TFP-1.0) — the OWASP MCP Cheat Sheet control "verify tool descriptions haven't changed", as an MCP tool: SHA-256 over the RFC 8785 JCS canonical form of each tool + a manifest fingerprint for the whole
tools/listsurface + drift reports (added / removed / changed) against pinned manifests. The core defense against tool poisoning and rug-pull redefinitions.MCP endpoint v1.11.0 (8 tools) and npm
marketnow-mcp@1.10.3(15 tools) — both new tools exposed; the npm package also fixes the brokenrepository.directorylink and upgrades the MCP SDK (DNS-rebinding advisory resolved;npm auditclean).Interceptor v1.1.0 (
@marketnow/cline-trust-plugin, npm) — revocation gate (fail-closed, 5-min TTL) + per-server tool-surface pinning/verification.Sentinel semgrep rules v2 — 29 rules: +tool-poisoning (MCP-TP), +exfiltration chains (MCP-EX), +multi-step attack chains (MCP-AC, roadmap v5.4 preview), +stale-trust caching (MCP-RR).
Rekor anchor #4 (logIndex 2771735480) — the revocation registry itself is anchored in Sigstore's public log; the revocation history is third-party-checkable end-to-end.
v1.3.3 — the receipts release (previous)
Stranger-verifiable trust evidence:
Rekor transparency anchors (entries #1–#3) — result digests committed to Sigstore's public append-only log; 9 local checks against live third-party data (run the stranger test above)
Stranger-verifiable trust evidence:
Rekor transparency anchors — result digests committed to Sigstore's public append-only log; 9 local checks against live third-party data (run the stranger test above)
Exercised CA key rotation —
mn-ca-002→mn-ca-003under suspected compromise, revocation published same-day, verifiers fail-safe inside the windowReproducible build —
agent-trust-card@1.1.2's tar layer rebuilds byte-exact from source (the.tgzis anchored by digest; the tar layer by rebuild)New failure vectors —
premature-atc(credential accepted before verification completes),expired-atc(key no longer valid at verify time), stage scoring, published generator CAConformance v1.3.3 — 14 public vectors · 24 checks + 10 mutants (runner-under-test) · versioned digests
v1.2.0 — Domain Reputation Endpoint (previous)
Domain Reputation Endpoint (/api/reputation) — UTA now answers a second class of trust
question. The Universal Trust API verifies credentials; this endpoint answers
"can I trust this domain before I show it to a human or act on it?"
Spec:
api/reputation-spec.md· v1.2 engine, stableReference implementation:
api/reputation.ts— one file, zero dependencies, hosting-neutral (Node 18+, Deno, Bun, Cloudflare Workers, any edge runtime)Verdicts:
trusted(95) ·unknown(55) ·caution(35) ·risky(8) — deterministic, transparent reasons, free & keyless, CDN-cacheable 24hClient parity: identical engine runs in the browser (ProdIntel
services/sourceTrust.ts) — badges render instantly offline, get server-confirmed when reachableFirst consumer in production: ProdIntel source safety gate
v1.2 engine fix: shortener matching is now exact-host/subdomain — v1.1 substring matching wrongly scored
riskymarketplaces containingt.coinside<name>.com(walmart.com, target.com, homedepot.com, flipkart.com). Cache consumers should key on v1.2.
Code lives in this repo (GitHub is the single source of truth). Deployment is bring-your-own-host.
ATC Versions in this repo
UTA supports TWO versions of ATC (Agent Trust Card):
Version | Status | Multi-sig | Spec file | Description |
ATC/1.0 | Public, stable | Single-sig (Ed25519) | Simple, single-CA credential. SDK at | |
ATC v3.0 | Draft 00, pre-public review | Multi-format (Ed25519 + EAT-CWT + W3C VC) | Multi-sig (N-of-M), multi-format. Backward-compatible with v2.0. Used internally by UTA. |
ATC v3.0 supersedes ATC v2.0 (which itself was the basis for the simpler ATC/1.0 SDK). A v2.0 ATC remains valid; v3.0 verifiers accept v2.0 credentials and treat them as having a single signature.
🚀 Quick install
# Multi-source installer (tries 5 channels in order)
curl -fsSL https://marketnow.site/install.sh | bash
# Or install individual packages
npm install agent-trust-card # ATC/1.0 SDK
npm install -g marketnow-mcp # MCP server (15 trust tools)
npx @marketnow/uta-conformance # run the 14-vector conformance suite
npx @marketnow/sentinel-rules --path . # 29 MCP security rules, zero-dep scan
npx marketnow-audit bit.ly # domain scam-check + ATC + OCSP, CI exit codes📊 Project stats
Metric | Value |
NPM packages | 11 (combined last-week downloads: 220+) |
Conformance (live) | 14 public vectors · 24 checks + 10 mutants · v1.3.3 |
Transparency anchors | 3 Rekor log entries (verify-rekor.mjs, 9 checks) |
CA key rotation | exercised 2026-09-08 ( |
Test vectors (ATC/1.0) | 5 frozen + manifest |
Test vectors (ATC v3.0) | 36 (8 positive + 17 negative + 5 mutation + 6 cross-language) |
Format adapters | 9 (ATC, EAT-AI, ZTA, A2A, MCP Card, W3C VC, OAuth, SPIFFE, X.509) |
Dev.to articles | 100 (EN + 15 languages) |
Download channels | 5 (NPM, jsDelivr, unpkg, marketnow.site, GitHub) |
📦 Packages
Package | Version | Description | Downloads (last week) |
1.10.3 | MCP server with 15 trust tools (+revocation, +fingerprinting; SDK hardened, | 76/wk | |
1.1.2 | ATC/1.0 SDK (issue, verify, inspect) | 27/wk | |
1.2.0 | Multi-source installer (5 stacks over the live catalog) | 15/wk | |
2.0.1 | Universal Trust Schema | 36/wk | |
2.0.0 | Trust Engine core: verification pipeline + behavior/drift + policy + trajectory + cross-agent (92 exports, zero deps) | 28/wk | |
1.0.2 | 9 format adapters (X509 exported; self-contained, zero deps) | 25/wk | |
1.0.3 | MCP middleware gateway + ReceiptStore/ReceiptGenerator exported (self-contained, zero deps) | 19/wk | |
1.1.0 | Cline interceptor: revocation gate + TFP tool-surface pinning | 0/wk | |
1.3.3 | 14 signed vectors + reference scorer + card generator — | 0/wk | |
1.0.0 | 29 MCP security rules: semgrep config + zero-dep lite scanner — | 0/wk | |
1.0.0 | MCP | new | |
1.0.0 | Zero-dep observability: structured logging, tracing, Prometheus metrics | new | |
1.0.0 | CLI credential verifier: ATC v3, JWT, VC, A2A, EAT, ZTA, MCP — CI exit codes | new | |
1.0.0 | Security audit CLI: domain scam-check, ATC verify, OCSP status, catalog — exit codes for CI ( | new |
🛡️ 5 Anti-ban download channels
NPM Registry — primary, independent of GitHub
jsDelivr CDN — free global CDN, mirrors NPM automatically
unpkg CDN — alternative CDN, also mirrors NPM
marketnow.site — AliceLabs-owned origin server
GitHub org —
alicelabs-llc/universal-trust-adapter(this repo)
📐 Open-Core Architecture
Layer | What | License |
1. Plugin Template | Interface + boilerplate for third-party adapters | MIT |
2. UTS Specification | Universal Trust Schema (spec + JSON Schema) | CC-BY-NC-ND 4.0 |
3. The Engine + Sentinel + Interceptor | TrustEngine core, 8-layer audit, eBPF enforcement | AL-1.0 |
🧪 Try it
# Verify any ATC card (ATC/1.0 or ATC v3.0)
npx -y agent-trust-card verify card.json
# Run the MCP server (works with Claude Desktop, Cursor, Cline, Continue, Aider)
npx -y marketnow-mcp
# Run the conformance suite
git clone https://github.com/alicelabs-llc/universal-trust-adapter
cd universal-trust-adapter/marketnow/atc-sdk
npm install && node test/conformance.mjs🧬 Test vectors
ATC/1.0 (5 frozen): marketnow/docs/atc-spec/test-vectors/ — 5 fixtures with canonical JCS bytes per vector + SHA-256 + Ed25519 signature.
ATC v3.0 (36 vectors): marketnow/docs/atc-spec/test-vectors-v3/ — 8 positive + 17 negative + 5 mutation + 6 cross-language.
The test CA keypair is intentionally published (including private key) for cross-language reproducibility.
📋 Specs & docs
ATC/1.0 Spec:
marketnow/docs/atc-spec/SPEC.mdATC v3.0 RFC Draft:
marketnow/docs/atc-spec/RFC-ATC-v3-Draft-00.mdDomain Reputation API spec:
api/reputation-spec.mdUniversal Trust API spec:
api/trust-api-spec.mdArchitecture:
docs/ARCHITECTURE.mdThreat model:
uta-repo/THREAT_MODEL.mdContributing:
CONTRIBUTING.mdSecurity policy:
SECURITY.md
🌐 Community
GitHub Discussions: discussions
Dev.to: @edison_flores_6d2cd381b13 — 96 articles
Issues: Report a bug
Email: info@alicelabs.site
📄 License
Component | License |
Plugin template | MIT |
UTS specification | CC-BY-NC-ND 4.0 |
Engine + Sentinel + Interceptor | AL-1.0 |
Author: Edison Flores · Email: info@alicelabs.site · Website: https://marketnow.site
Company: AliceLabs LLC (Wyoming, USA)
License
Dual-licensed under MIT OR Apache-2.0, at your option — free for any use, including commercial use. This repo and all MarketNow npm packages (marketnow-mcp v1.14.0+, agent-trust-card v1.4.0+, @marketnow/*) ship dual-licensed: see LICENSE-MIT and LICENSE-APACHE. Trademarks ("MarketNow", "UTA", "ATC") are reserved by AliceLabs LLC — see NOTICE.
Related MCP Connectors
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Give AI agents identity, permissions, and reusable proof through one MCP.
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceOn-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.1-
- AlicenseAqualityAmaintenanceMCP server for checking supply-chain trust before connecting to AI agents, frameworks, or MCP servers.839 npm1MIT
- AlicenseAqualityDmaintenanceMCP server for AI agent trust verification, enabling agents to verify identities, check trust scores, and build reputation across multiple blockchain and web platforms.1210 npm1MIT
- FlicenseNot gradedqualityCmaintenanceProvides trust infrastructure for AI agents by enabling reputation lookup, website trust scanning, and identity verification via MCP tools.1-