Vaneform

io.github.jiangqizheng由 GitHub 账号 jiangqizheng 发布v1.4.3更新于 Oct 24, 2026

Free website traffic checker: monthly visits, traffic sources, top countries and domain compares.

已验证Streamable HTTP可网页运行网页搜索与抓取数据与分析

概览

AI 生成的概览

Vaneform 通过托管 MCP 端点,让助手查询网站估算流量、对比域名并获取关键词数据,使用基于积分的 API 密钥。

可以做什么
  • 查询域名的缓存快照:访问量、注册信息、站点画像与链接排名热度
  • 并排对比多个域名,或对比同一名称的不同后缀
  • 读取美国/英文关键词简报:搜索量、难度、CPC 与 Google 占位(Pro)
  • 对 Google Ads、Meta 广告、AdSense 与外链进行免费站点调研
  • 保存、监控并管理私有调研目标、文件夹与变更通知
  • 查看账户套餐、查询额度与积分余额
适用场景
适合让助手回答某网站流量多少、两个网站如何对比、某关键词的搜索量与 CPC 等问题,并持续跟踪广告或域名变化。
运行要求
远程 Streamable HTTP 端点位于 vaneform.com;需要 Vaneform API 密钥,通过 Authorization bearer 头传递(也接受 X-API-Key)。免费账户每月 100 积分。也可用 npx 运行本地 stdio 代理,需 Node 18 或更高版本及 VANEFORM_API_KEY 环境变量。
安装前请注意
API 密钥属于机密,勿写入共享配置。查询会消耗积分:每域名 1 积分、关键词简报 60 积分、Pro 站点关键词排名 200 积分,批量调用可能耗尽月度额度。保存的调研、监控与笔记会写入你的 Vaneform 账户。流量数据为第三方估算,并非实测分析。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Vaneform,将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.jiangqizheng%2Fvaneform-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "vaneform": {
      "type": "http",
      "url": "https://vaneform.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

vaneform-mcp

[CI] [License: MIT] [Listed on mcpservers.org]

Website traffic lookups for AI assistants and the terminal. This repo has an MCP server, a small CLI and an agent skill for Vaneform, a free website traffic checker.

Ask your assistant "how much traffic does notion.so get?" or "compare figma.com and canva.com" and it answers with estimated monthly visits, month-over-month change, rank, top countries, traffic sources and registry facts. Traffic figures are third-party traffic estimates; see the Vaneform methodology.

中文说明

What's inside

PieceWhat it is
Hosted MCP serverhttps://vaneform.com/mcp (Streamable HTTP). Zero install, and the recommended option.
vaneform-mcpLocal stdio MCP server for clients that only run local commands. It proxies the hosted server, so tools never drift.
vaneform CLIvaneform notion.so, vaneform compare a.com b.com, vaneform tld name. It shares the same client.
skills/website-traffic-lookupAgent skill (Claude / Agent Skills format) that tells an assistant when to check traffic and how to read and cite the result.

Tools

These tool names and descriptions come from the hosted server's tools/list:

ToolWhat it doesCost
lookup_domainCached snapshot of a domain: visits (full-site or search), registry, site profile, link-rank popularity1 credit
compare_bulkSide-by-side visits and registry for several domains; fetches traffic when it is missing1 credit per domain
compare_tldOne name across suffixes (default com,ai,io)1 credit per domain
get_accountPlan and remaining creditsfree
lookup_keywordUS keyword brief: volume, difficulty, CPC, Google occupancy (Pro)60 credits

Repeating a domain lookup within 24 hours is free. Site keyword rankings (Pro, 200 credits) are available through the API with include=search.

Free vs Pro

FreePro
Credits per month10010,000
API key, MCP and CLI✓✓
Domain lookup and compare (1 credit per domain, repeats within 24h free)✓✓
Keyword brief (60 credits)✓
Site keyword rankings (200 credits)✓

Each key allows 60 requests a minute and 5,000 a day (429 lookup_rate_exceeded above that). See pricing.

Get a free API key

Discovery (initialize, tools/list) is open. Tool calls need a Vaneform API key.

  1. Sign in at vaneform.com and create a key at vaneform.com/account/api. A free account is enough.
  2. Remote: send Authorization: Bearer vf_live_… or X-API-Key: vf_live_…. Local server and CLI: set VANEFORM_API_KEY.

Without a key, tools still list, and a call returns a sign-up link plus a browser link such as https://vaneform.com/?q=notion.so.

Install

Claude Code (remote)

bash
claude mcp add --transport http --scope user vaneform https://vaneform.com/mcp \  --header "Authorization: Bearer vf_live_…"

Cursor (remote)

~/.cursor/mcp.json (or .cursor/mcp.json in a project):

json
{  "mcpServers": {    "vaneform": {      "url": "https://vaneform.com/mcp",      "headers": { "Authorization": "Bearer vf_live_…" }    }  }}

Claude Desktop (local stdio)

The simplest Claude Desktop setup that passes your key is the local proxy. Edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

json
{  "mcpServers": {    "vaneform": {      "command": "npx",      "args": ["-y", "github:vaneform/vaneform-mcp"],      "env": { "VANEFORM_API_KEY": "vf_live_…" }    }  }}

The package isn't on npm yet, so npx installs it from GitHub. The first start takes a little longer because it builds once. If npx exits right away on an old system npm (Debian's packaged npm 9.2 does this with GitHub packages), run npm install -g github:vaneform/vaneform-mcp and use "command": "vaneform-mcp" with no args.

Codex

bash
export VANEFORM_API_KEY=vf_live_…codex mcp add vaneform --url https://vaneform.com/mcp --bearer-token-env-var VANEFORM_API_KEY

Any other MCP client

  • Remote: URL https://vaneform.com/mcp, transport Streamable HTTP, header Authorization: Bearer vf_live_… (or X-API-Key: vf_live_…)
  • Local: command npx -y github:vaneform/vaneform-mcp, env VANEFORM_API_KEY

CLI

bash
npx -p github:vaneform/vaneform-mcp vaneform --help# or clone, then: npm install && npm linkexport VANEFORM_API_KEY=vf_live_…vaneform notion.so                       # traffic overviewvaneform compare notion.so coda.io       # side by sidevaneform tld vaneform --suffixes com,ai,iovaneform account                         # plan and remaining credits (free)vaneform notion.so --json                # raw API JSON

Output with no key set:

text
$ vaneform toolslookup_domain   Read a cached Vaneform domain snapshot: scale (full-site or search visits), registry, site profile, and link-rank popularity.get_account     Read the caller plan, website lookup allowance, and credit balance.lookup_keyword  Read a US/EN keyword brief: monthly searches, difficulty, CPC, and Google occupancy.compare_bulk    Compare domains side by side.compare_tld     Compare the same registrable name across suffixes.
$ vaneform github.comVANEFORM_API_KEY is not set, so this tool cannot call the Vaneform API.Create a free API key at https://vaneform.com/account/api (100 credits a month; 1 credit per domain).Check it in a browser instead: https://vaneform.com/?q=github.com

With a key, vaneform <domain> prints visits, MoM change, rank, top countries, sources, registry dates and the report link, followed by Data: Vaneform (third-party traffic estimates).

Talk to the hosted server directly

bash
curl -s https://vaneform.com/mcp \  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

The same key works for the REST API: docs, OpenAPI.

Agent skill

Copy the skill so your assistant knows when to reach for traffic data and how to cite it:

bash
# Claude Code (user-wide)mkdir -p ~/.claude/skills/website-traffic-lookupcurl -fsSL https://raw.githubusercontent.com/vaneform/vaneform-mcp/main/skills/website-traffic-lookup/SKILL.md \  -o ~/.claude/skills/website-traffic-lookup/SKILL.md

For other agents that read SKILL.md folders, put it in that agent's skills directory (for example .agents/skills/ in a project). Vaneform also serves a lower-level API skill at vaneform.com/skill.md.

Reading the numbers

  • status: "missing" means Vaneform hasn't cached that domain yet. It does not mean zero traffic. compare_bulk fetches it.
  • Every estimate carries its month (as_of) and a confidence label. Quote them.
  • Cite results as "Vaneform (third-party traffic estimates)".

Development

bash
npm install        # also builds dist/npm run lint       # biome + tscnpm test           # unit tests + a stdio test with the official MCP SDK clientVANEFORM_MCP_URL=http://localhost:3000/mcp node dist/bin/vaneform.js tools   # point at another server

The runtime has no dependencies and needs Node 18 or newer. This repo contains only the client. No data collection code lives here.

License

MIT. The license covers this code only, not data returned by the API. Traffic figures are third-party estimates served by Vaneform.

来源:README.md,提交 676ff98

工具

10

research_site

Free early-access standalone site research. Query Google ads by domain or advertiser, public Meta ads by keyword, AdSense accounts/related sites, outbound page links, collected ad text, recorded website opportunities or DR changes. Source acquisition is explicit and bounded; all these tools spend 0 credits. Ad text and Publisher ID reverse lookups cover the recorded collection. Estimates and observations retain dates, scope and confidence.

输入参数q必填modetool必填limitmaxDrminDrcursorregionmaxVisitsminVisitsmaxAgeMonths

get_research_workspace

Read the caller saved research, folders, private notes, tool history, publisher/ad monitors and in-app change notifications. Free; 0 credits. Account ownership comes from the authenticated key.

无需输入参数。

save_research

Save a standalone site-tool query in the caller workspace, with a folder and private notes. Free; 0 credits.

输入参数label必填notes必填query必填folder必填

monitor_research

Monitor a Google Ads or AdSense query daily or weekly. Record newly observed public ads and connected sites as private in-app notifications. The first successful observation establishes a baseline. Free; 0 credits.

输入参数label必填query必填interval_days必填

manage_research

Manage the caller private research: remove a saved target, pause/resume or change daily/weekly monitoring, remove a monitor, check current public data, or mark a change notification read. Use IDs from get_research_workspace. Free; 0 credits.

输入参数id必填action必填activeinterval_days

lookup_domain

Read a cached Vaneform domain snapshot: scale (full-site or search visits), registry, site profile, and link-rank popularity. Optional include=baidu is cached Baidu rank. Optional include=search is Pro-only keyword rankings (ranked keywords, landing pages, search competitors) from this month's cache. Cache-only: status=missing means not cached, not zero traffic. Use for 查网站, 访问量, how big a site is, domain visits, registry age, backlink rank, 百度权重, or 关键词排名. A new ready or partial domain spends 1 credit, or 10 when include=search finds no saved ranking or a saved ranking whose status is ready. include=search spends 0 when that saved status is missing, error, or partial.

输入参数domain必填include

get_account

Read the caller plan, website lookup allowance, and credit balance. This call spends 0. Use before a batch.

无需输入参数。

lookup_keyword

Read a US/EN keyword brief: monthly searches, difficulty, CPC, and Google occupancy. Pro-only. At most 30 Google results. A cache hit is free; a successful miss spends 60 credits. After trimming, longer than 200 characters is invalid. Matching uses the lowercased, space-collapsed first 80 characters. Use for 关键词查询.

输入参数q必填

compare_bulk

Compare domains side by side. Returns scale and registry. Fetches traffic when monthly visits are missing. Spends 1 credit per compared domain with data. Up to 3 domains on Free, 30 on Pro. Use for 批量对比.

输入参数q必填

compare_tld

Compare the same registrable name across suffixes. Default suffixes are com,ai,io. example.com is read as example. Response suffixes and items follow a fixed suffix order; match the returned suffixes. Fetches traffic when monthly visits are missing. Spends 1 credit per compared domain with data. Use for 后缀对比.

输入参数q必填s

版本历史

4
  1. v1.4.3最新Oct 18, 2026
  2. v1.4.2Oct 15, 2026
  3. v1.4.1Oct 11, 2026
  4. v1.4.0Oct 10, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分