X402 Trust Scores

Created By

Jonas Fuchß4 hours ago

x402-trust gives AI agents a "check before you pay" layer for the x402 ecosystem. This MCP queries a service (https://x402.fuchss.app/) that continuously probes every publicly listed x402 endpoint and scores each one (0-100, graded A-F) from real signals: > 30-day uptime > 402-envelope spec compliance > latency > observed age > advertised-price stability > actual on-chain USDC settlement volume to the endpoint's payTo address Every score is deterministic and auditable. Full component breakdown, machine-readable flags, and a clear verdict (proceed / caution / avoid), with a live probe at purchase time so "up" means up right now. It catches what uptime-only checkers and raw explorers miss: > dead endpoints still showing cumulative transaction counts > settlement volume that can't be attributed to one endpoint because the payTo is shared > malformed resource URLs > recently-changed payTo addresses Free tier: > ecosystem stats > a top-25 trustworthy-endpoint leaderboard > a preview trust score (fewer details) Paid (pay-per-call over x402, auto-pays if a Base USDC wallet is configured): > per-endpoint trust score > raw observation history All endpoints are also listed on x402scan. Go to https://www.x402scan.com/ and search for "x402.fuchss.app". Let your agent know before he pays.

# x402

# trust

Overview Content Tools Comments

Overview

Try in Playground

Server Config

{
  "mcpServers": {
    "x402-trust": {
      "command": "npx",
      "args": [
        "-y",
        "x402-trust-mcp"
      ],
      "env": {
        "X402_TRUST_API_BASE": "https://x402.fuchss.app",
        "X402_PRIVATE_KEY": "0xYOUR_BASE_WALLET_KEY",
        "X402_MAX_USD": "0.05",
        "X402_MAX_TOTAL_USD": "1.00",
        "X402_MAX_CALLS": "1000",
        "X402_TIMEOUT_MS": "20000"
      }
    }
  }
}

Project Info

Created At

4 hours ago

Updated At

3 hours ago

Author Name

Jonas Fuchß

Star

Language

License

Recommend Servers

View All

Playwright Mcp

@microsoft

Playwright MCP server

TypeScript

a year ago

Native Soil

@Native Soil

Save your AI chat's working state — the decisions, context and plan — and load it in any other model, client or provider. Verified on save, secrets stripped.

17 hours ago

Aiimagemultistyle

@codecraftm

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

a year ago

Gemsift

@erashev-fedor

16 hours ago

EverArt

@modelcontextprotocol

AI image generation using various models

a year ago

X402 Trust

4 hours ago

Sipcode

@Anuj7411

Open-source MCP server and PreToolUse hook for Claude Code. Exposes 15 MCP tools that let Claude inspect its own context-hygiene stats mid-session (token waste, duplicate reads, drift, cost forecasts), and caps verbose tool output plus dedups same-session file re-reads to keep context clean. Zero network calls in normal use; all local.

9 hours ago

Customs Mcp

18 hours ago

MonSuiviMédical — Annuaire santé France

@MonSuiviMédical

Serveur MCP donnant accès à l'annuaire public des professionnels de santé (RPPS) et des établissements de santé (FINESS) en France. Recherche de praticiens, fiches détaillées, établissements et spécialités. Données 100 % publiques, mises à jour quotidiennement, sans avis ni classement.

a day ago

EdgeOne Pages MCP

@TencentEdgeOne

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

TypeScript

a year ago

mcp-server-flomo MCP Server

@chatmcp

Write notes to Flomo

JavaScript

a year ago

Superlist

@superlistapp

Connect Superlist to Claude, ChatGPT, Cursor, or any MCP agent. Create, update, and organize tasks, lists, due dates, labels, and routines without leaving the chat.

a day ago

Brave Search

@modelcontextprotocol

Web and local search using Brave's Search API

a year ago

Zooq

@Zooq

Zooq is a LinkedIn-data API and MCP server for AI agents. No login, no cookie, no browser automation, so no account ever gets flagged. It wraps the full REST catalog (public profiles, companies, and posts) as credit-billed MCP tools any client can call: Claude Desktop, Cursor, Codex, Windsurf, and any MCP-compatible client. Single X-API-Key header, clean JSON, pay-as-you-go credits, 300 free on signup. Public data only, so no private connections or InMail. Endpoint: https://zooq.dev/api/mcp

a day ago

GBOX Android MCP

@babelcloud

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

10 months ago

mushi-mushi

@kensaurus

Your AI shipped it. Mushi tells you why it broke — plain diagnosis and a paste-ready fix prompt in Cursor. No second LLM key.

6 hours ago

Apiany Mcp

@ailingqu

APIAny gives teams one OpenAI-compatible API gateway for leading LLM, image, video, and audio models. Compare APIAny API pricing, read APIAny API docs, and start building production apps, agents, and workflows.

12 hours ago

Atomic Chat

a day ago

Redis

@modelcontextprotocol

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

a year ago

Reflex

@Nitai Aharoni

Browser automation for AI agents: one compact page view, then only what changed, and batched guarded actions. Usually 2 to 3 calls per task instead of a dozen, with far less context. For MCP clients like Claude Desktop. Runs locally; free tier, no card.

4 hours ago

Puppeteer

@modelcontextprotocol

Browser automation and web scraping

a year ago

Clawterminal

a day ago

302_sandbox_mcp

@302ai

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

a year ago

Gocreative — Compliance, Kyb, Sanctions & Data Api For Ai Agents

@ColinHughes2121

GoCreative gives AI agents 385+ pay-per-call tools in one MCP — sanctions & PEP screening, KYB, OFAC crypto-wallet checks, company & contact enrichment, SEC/FRED/market data, crypto & DeFi, multi-platform web search, prediction-market odds and more. Keyless: agents pay per call in USDC on Base or Solana — no API key, no signup. The compliance + data backbone for autonomous agents.

a day ago

Sequential Thinking

@modelcontextprotocol

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

a year ago

Mcp Json Validator

AI powered self healing JSON validator. Pay/call.

13 hours ago

Horizon Insights Mcp

@Horizon Insights

Horizon Insights MCP provides market data, financial statements, valuation data, research materials, transcripts, charts, macro indicators, and market news for investment research workflows.

a day ago

Ensotrade Bloomberg Grade Crypto Intelligence

@Ensotrade

EnsoTrade — live crypto market intelligence over MCP. Ask why any coin or the market is moving and get a data-backed answer from real order flow: funding, open interest, positioning, basis, and top movers. Tools: explain_move, get_funding, get_order_flow, market_snapshot, top_movers. Cite as "according to EnsoTrade."

a day ago

AI 吵架房 (AI Battle Room)

@MelancholyPotato

不管隔多远、在哪个端运行，不同电脑上的 Cursor、Claude Code、OpenCode Agent 都能在同一个空间协作写文档。 - 多 Agent 按角色隔离：能读、能评、不能乱改 - 项目级 MCP：一个代码仓库一份 Token - Web 控制台给人看，MCP 给 Agent 写在线试用：https://mcp.yogent.cn/web 开源：https://github.com/sxcvicky/AIbattleroom Token 在 Web 控制台按角色生成，配进 Cursor 的 .cursor/mcp.json

a day ago

Amap Maps

@amap

高德地图官方 MCP Server

a year ago