原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

New X402 Listings Feed

作者:nexus-mcp-infra版本 1.0.0i★ 0i在云端运行代码仓库 ↗
注册名称io.github.nexus-mcp-infra/new-x402-listings-feed

安装方法

能做什么

Feed of x402/L402 services newly listed on 402index.io within a recency window (candidate #8, manual

作者提供的原文

  • 连接方式 在云端运行
  • 账号或密钥 可能需要密钥,尚无法确认(检查被拒绝)
  • 分类 其他

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度7/1230 天内有发布或代码更新得满分
仍在响应8/8上次检查时云端端点有响应
使用分15/100

质量: 基础检查通过 2/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 New X402 Listings Feed。按照 https://mcp.popnx.com/i/nexus-mcp-infra-new-x402-listings-feed.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 2/5 项检查 · 你的提问会经过开发者的服务器(new-x402-listings-feed-325572559480.us-central1.run.app) · ✓ 命令已检查 2026年11月20日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称New X402 Listings Feed
    Remote MCP server URL · 地址https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsNew X402 Listings Feed

  4. 试一试

    用 New X402 Listings Feed 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 New X402 Listings Feed,或回答中出现 New X402 Listings Feed 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称New X402 Listings Feed
    Connection · 地址https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp
  3. 在聊天中选择 New X402 Listings Feed

    开启新聊天,输入前先从插件列表中选择 New X402 Listings Feed

  4. 试一试

    用 New X402 Listings Feed 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 New X402 Listings Feed,或回答中出现 New X402 Listings Feed 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user new-x402-listings-feed https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 New X402 Listings Feed 在列表中并显示已连接

  4. 试一试

    用 New X402 Listings Feed 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 New X402 Listings Feed,或回答中出现 New X402 Listings Feed 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 New X402 Listings Feed 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 New X402 Listings Feed,或回答中出现 New X402 Listings Feed 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 New X402 Listings Feed 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 New X402 Listings Feed,或回答中出现 New X402 Listings Feed 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 New X402 Listings Feed 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user new-x402-listings-feed https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "new-x402-listings-feed": {
      "url": "https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "new-x402-listings-feed": {
      "type": "http",
      "url": "https://new-x402-listings-feed-325572559480.us-central1.run.app/mcp"
    }
  }
}

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
不在 npm/PyPI 上
许可证i
未注明许可证
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.0.0
分类i
其他
发布到注册中心i
2026年8月23日
代码最后更新i
2026年9月4日
最近检查
2026年11月15日
作者
nexus-mcp-infra
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

服务器要求先登录,才会列出它的工具。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 nexus-mcp-infra 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3个月前

  • ✕ 未通过

    有许可证

    仓库中没有找到许可证文件

  • ! 注意

    端点有响应

    拒绝访问(HTTP 403),且未提供 OAuth 登录。可能需要密钥,也可能是拦截机器人,尚未确认。

  • ! 注意

    使用 OAuth 登录

    需要你自己复制粘贴密钥或令牌

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/nexus-mcp-infra-new-x402-listings-feed.svg)](https://mcp.popnx.com/en/servers/nexus-mcp-infra-new-x402-listings-feed)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20958 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 20958 个服务器的 24% 更新
  • 基础检查结果等于或优于此分类中其他 20958 个服务器的 7%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

New X402 Listings Feed 安全吗?

它在 5 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于3个月前,最新版本(1.0.0)于3个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万4天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92762个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582414个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
New X402 Listings Feed
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
运行位置在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查2/54/44/44/41/44/4
许可证–AGPL-3.0AGPL-3.0MITApache-2.0MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

New x402 Listings Feed

Feed of x402/L402 services newly listed on 402index.io within a caller-specified recency window. NEXUS candidate #8 -- manual build, not FORGE-generated, same manual-Cloud-Run-asset pattern as candidates #3 (agent-verification-api), #4 (url-metadata-api) and #6 (document-conversion-api).

  • POST /new-x402-listings {"window_hours": 24, "protocol": null, "category": null, "payment_network": null} -- services registered on 402index.io within the window (1-168h, default 24). $0.01/call.
  • MCP tool get_new_x402_listings at /mcp, same params -- currently free, see "Known limitations".
  • GET /health, GET /.well-known/agent-card.json, GET /openapi.json (has x-payment-info), GET /.well-known/402index-verify.txt (402index claim verification file).

Mainnet cutover (2026-09-03)

Originally built and measured on Base Sepolia testnet. Cut over to Base mainnet: x402 settlement moved to the CDP facilitator (create_facilitator_config(), same swap already applied to ws/live-entity-verification/erc8004-agent-liveness/onchain-activity-index/x402-receipt-verifier), and the payto wallet moved to NEXUS_X402_PAYTO_ADDRESS (fail-fast env var, no placeholder default, renamed from X402_WALLET_ADDRESS). CDP_API_KEY_ID/CDP_API_KEY_SECRET and NEXUS_X402_PAYTO_ADDRESS must be set in Cloud Run before this deploys.

What this is (and isn't)

This is not exclusive data. The registration data underneath this asset is 402index.io's own free, public directory (https://402index.io/api-docs, no auth needed, 100 req/min free tier). Anyone can query it directly for nothing. This asset's value is entirely in the packaging: polling and paginating the ~96k+ entry catalog so a buyer doesn't have to, merging in 402index's own recency feed for freshness, deduping, and filtering to a caller's window/protocol/category/payment-network. This disclosure is not just in this README -- it's baked into the product itself: every response includes a note field stating it plainly, and the agent-card's protocol_note repeats it, so a buyer never has to dig for it.

Feasibility research (2026-08-23, before writing any code)

The task brief's premise cited a prior-session figure of "~7,595 total services" on 402index.io. A real curl https://402index.io/api/v1/services?limit=5 at the start of this session showed "total": 96093 -- the catalog grew roughly 12x since that check. registered_at is real and populated on every entry sampled. Two upstream mechanisms were verified live, each with a real limitation neither the task brief nor 402index's own docs fully surfaced:

  1. `GET /api/v1/services` (paginated, limit/offset, max 200/page) has NO sort-by-date or date-range filter -- sort only accepts name/price/latency/uptime/reliability (checked /api-docs directly). A window query can only be answered by walking the *entire* catalog and filtering client-side -- there is no cheaper server-side path. At the real current size that's ~481 pages, not the ~40 pages the ~7,595 figure would have implied.
  2. `GET /feed.xml?type=new` is real, RSS 2.0, and IS already recency-sorted (pubDate) -- and is on 402index's own documented rate-limit-exempt list. But it's capped to a fixed item count: a live fetch during this session returned exactly 90 items spanning only ~3 hours, despite the docs describing type=new as "services added in the last 7 days". At current registration velocity it does not cover a 7-day (or even a 24h, at peak velocity) window by itself.

Neither source alone honestly satisfies the product's advertised window range. Decision: proceed, using both. See the main.py module docstring and "Architecture" below for how they're combined. This is the kind of real, current-data discrepancy CLAUDE.md SS3 asks to surface rather than build past silently -- so it's recorded here rather than only in a chat transcript.

Architecture

  • A background asyncio task (started in FastAPI's lifespan, not blocking startup) walks the full /api/v1/services catalog every NEXUS_CATALOG_REFRESH_SECONDS (default 600s/10min), paced at 0.65s/request (~92 req/min sustained, safety margin under 402index's 100 req/min free-tier cap). Results are cached in memory (_catalog_cache), keyed by service id. A full walk at the current catalog size is ~481 pages / ~5.2 minutes -- entirely a background-task cost, never inline in a buyer's request.
  • Every buyer request additionally fetches /feed.xml?type=new live (rate-limit-exempt, ~1 request, cheap) and merges it into whatever the background walk has cached, catching anything registered after the last completed walk. Cache entries win on id conflict (richer fields); feed entries only fill gaps.
  • Response is filtered/deduped/sorted (newest first) from that merge, capped at 500 results.
Why not a literal TTL cache (deviation from the task brief's suggested shape)

The brief suggested "a short in-memory cache (5-10 min TTL)". Implemented instead: a continuously-running background loop that re-walks every 10 minutes and replaces the cache, with buyer requests always reading whatever is currently cached (never triggering a walk themselves). A literal on-demand-when-stale TTL would mean whichever buyer request happens to arrive right after expiry pays $0.01 and then blocks for up to ~5 minutes waiting on a fresh 481-page walk -- unacceptable buyer experience found during design, not retroactively. The background-loop shape gets the same "don't hammer 402index.io" goal without ever making a paying caller wait on the walk.

Cold start (Cloud Run scale-to-zero)

min-instances=0 means a fresh container starts with an empty cache. The first request(s) after any period of inactivity get catalog_walk.status: "cold_fallback_feed_only" -- results are limited to whatever /feed.xml?type=new currently holds (recently observed to span only a few hours), not the full requested window. This is disclosed in the response's own note field, not hidden. Once the background task's first walk completes (~5 minutes after container start), subsequent requests get status: "warm" with full catalog-walk coverage. Genuinely mitigated, not solved -- see "Known limitations".

Pricing: $0.01/call (low tier)

Speculative niche per the product owner (explicit direction, not a data-driven conclusion) -- same low tier as url-metadata-api/document-conversion-api's $0.01-$0.02, not agent-verification-api's $0.35 signal tier. No paid third-party API cost, pure CPU/memory + one free upstream fetch per call.

Pre-deploy quality gate (2026-08-23, from design not retroactive)

Reviewed across 4 lenses before first deploy, tested against the real live 402index.io API (not mocked) at each step. Real findings and fixes:

  • Security: caller input (window_hours/protocol/category/payment_network) is never interpolated into the upstream 402index.io request -- the catalog walk and feed fetch use fixed, hardcoded query params only (limit/offset/sort/order and type=new respectively); caller filters apply exclusively to the already-fetched, normalized in-memory result. Verified upstream JSON/XML is never trusted blindly: every field read via .get() with type checks (_normalize_catalog_item returns None on a malformed entry rather than raising), malformed XML from /feed.xml is caught (ET.ParseError) rather than crashing the request, and a single malformed in the feed doesn't drop the rest of it. All confirmed with real malformed-input tests (None, missing id, wrong types, garbage timestamp, truncated XML) during this session, not just read as correct.
  • Functional correctness (real gap, fixed): the initial design cached complete: bool internally but never surfaced it in the response -- a caller had no way to tell a background walk that hit the _WALK_MAX_WALL_SECONDS wall-clock cap (bailing out with a partial result) from one that finished cleanly, even though both report status: "warm". Fixed: added catalog_walk.walk_complete to the response. Pagination itself (offset advance, stop-at-total, wall-cap bailout) was verified against the real live API with a bounded test walk (8 real pages, offset advancing correctly, graceful bailout logged) -- no silent truncation, no infinite loop.
  • Code quality: no dead code or unused imports found in review; matches sibling assets' structure (Supabase telemetry helpers, x402 wiring, discovery routes) ported by hand, consistent with how document-conversion-api/url-metadata-api are built.
  • Buyer experience (the "raw data is free elsewhere" disclosure lens): the fact that 402index.io's data is itself free was verified present in 3 places, not just the README: the agent-card protocol_note, and -- more directly, so no buyer has to fetch the agent-card at all -- every single API response's own note field. Cold-cache degraded coverage (cold_fallback_feed_only) is also disclosed in that same note field with plain language about what it means for the requested window, not just a status enum a caller has to already know how to interpret.

Known limitations (left as documented tradeoffs, not silently)

  • MCP tool calls are not charged. Same in-process-call pattern as the sibling manual assets.
  • No per-caller rate limiting. Fine for a 7-day disposable measurement window.
  • Cold-cache window under-coverage is mitigated, not solved. A request landing in the first ~5 minutes after a Cloud Run cold start gets feed-only coverage (recently observed ~3h span for a 90-item feed at current 402index velocity), not the full requested window, even though it's charged the same $0.01. This is disclosed live in the response, but a buyer who calls once, right after a cold start, and doesn't read catalog_walk.status/note could reasonably read a short result list as "nothing new" rather than "cache still warming up". A future fix could hold min-instances=1 to eliminate cold starts entirely, at a real always-on Cloud Run cost -- not done for a 7-day probation candidate.
  • `registered_at` is assumed UTC. 402index's /api/v1/services returns naive timestamps ("2026-08-22 22:13:15", no offset) -- treated as UTC based on consistency with last_checked values observed live during this session, not a documented guarantee from 402index.io itself.
  • Full-catalog walk pacing assumes today's catalog size. At ~96k entries a full walk is ~481 pages/~5.2min, safely inside the 10-minute refresh interval. If 402index's catalog keeps growing at the ~12x-since-last-check rate observed this session, a future walk could approach or exceed the 10-minute refresh interval (it would then just take longer between the visible "last_full_walk_at" updates, not break -- _WALK_MAX_WALL_SECONDS bails a single cycle out at 900s and walk_complete reports it honestly) -- not re-engineered preemptively per CLAUDE.md SS3 (no gate without evidence it's needed yet).

NEXUS_X402_FREE_MODE

Default false (charges from day 1, no freemium window) -- same convention as document-conversion-api. Set true locally for testing without a real facilitator round-trip.

Deploy target: Cloud Run, not Railway

Same pipeline as candidates #3/#4/#6 -- see skills/infra-deploy-ops. No PDF/Office parsing here, so the shared script's default 512Mi is used (not bumped to 1Gi like document-conversion-api).

# 1. First deploy -- PUBLIC_DOMAIN not known yet, every real request 421s until step 2.

./scripts/deploy_cloud_run.sh new-x402-listings-feed manual_assets/new-x402-listings-feed \ manual_assets/new-x402-listings-feed/env-vars.deploy.yaml

2. Grab the printed *.run.app URL, then:

gcloud run services update new-x402-listings-feed --region us-central1 --project nexus-505016 \ --update-env-vars P

只显示了开头部分;其余内容请在仓库中阅读