INITE Visibility

ai.inite由 inite.ai 發布官方發布者v2.1.0更新於 Oct 27, 2026

How ChatGPT, Claude, Gemini and Perplexity read a site: free check, fix plan, compare, history.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取開發者工具資料與分析

概覽

AI 產生的概覽

檢查 AI 答案引擎如何看待某個網站——爬蟲權限、身分檔案、結構化資料——並給出可見度評分、修正方案與競品比較。

可以做什麼
  • 在本機檢查爬蟲存取權限、身分檔案與頁面訊號,不需帳號
  • 讀取網站的 AI 身分評分與最該優先修正的項目
  • 取得依優先順序排列的修正方案,含可直接貼上的片段
  • 將網站與競品以相同標準並排比較
  • 啟動 AI 可見度稽核並查詢進度與分數
  • 查看可見度歷史,登入後還可查看自己的報告
適用情境
想知道 ChatGPT、Claude、Gemini 或 Perplexity 能否找到並引用某個網站,以及該改什麼才能被引用時使用。適合 SEO/AEO 優化、上線前檢查與競品比較。
執行需求
可作為本機 npm 套件透過 npx 執行(需 Node.js),也可直接連線 inite.ai 的遠端端點。本機檢查與開放的遠端工具不需帳號;透過瀏覽器登入或設定 INITE_TOKEN 可解鎖帳號層級的稽核與報告。遠端工具需要能連線 inite.ai。
安裝前請注意
登入後會把存取權杖存放在本機磁碟(預設在使用者設定目錄下),也可透過 INITE_TOKEN 提供,應視為憑證妥善保管。稽核與比較會把目標網站位址傳送到 inite.ai。含答案引擎查詢的完整稽核僅限付費方案,訪客使用依位址限流。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 INITE Visibility,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.inite%2Finite-visibility/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "inite-visibility": {
      "type": "http",
      "url": "https://inite.ai/api/mcp/analyzer"
    }
  }
}

README

INITE MCP — AI visibility, from inside your agent

Ask your assistant whether the answer engines can see a website, and get a number back.

> Can ChatGPT actually find stripe.com, or is it invisible?
  analyze_site(url: "stripe.com")   → run_id: cm4x…  get_analysis(run_id: "cm4x…")     → Score: 78/100

The audit reads a live site the way an assistant does — the identity files an engine looks for (llms.txt, ai.json and the rest), the crawler policy, the schema graph, page health — and then asks Claude, ChatGPT, Gemini and Perplexity whether they name it. One score out of 100 across eight weighted sections.

It is the same audit that runs at inite.ai/en/analyze.

Works before you sign in

Three of the tools run entirely on your machine — a robots.txt fetched, a file probed for, a page parsed. No account, no allowance, no call home.

> Is anything blocking AI crawlers on stripe.com?
  check_ai_access(url: "stripe.com")
  Retrieval: all 7 answer-engine crawlers may fetch the site.  Training:  3 of 8 blocked — Meta-ExternalAgent, Bytespider, Amazonbot.

The rest is inite.ai's AI visibility server, and it answers signed out too, as a guest: check_identity, the fix plan (visibility_fixes), a competitor read the same way (compare_sites), how the reading moved (visibility_history), and analyze_site as the survey - the audit without its two paid steps, two a day per address.

> What should firecrawl.dev fix first so ChatGPT can use it?
  visibility_fixes(url: "firecrawl.dev")
  1. [critical] No structured data on the site (about +3.5 points)     Do: Add Organization (and WebSite) JSON-LD to every page.  2. [high] 7 retrieval crawlers are blocked on …

Visibility and nothing else. INITE's services and booking are ai.inite/inite, the catalogue of AI tools is ai.inite/atlas.

Signing in makes the calls your account's: its tier of the audit (the teaser on a free plan, the whole audit on a paid one) and your audits: my_reports, and the fix plan and history built from them.

Install

Claude Desktop, Cursor, or any client that launches a stdio server:

json
{  "mcpServers": {    "inite": {      "command": "npx",      "args": ["-y", "@inite/visibility"]    }  }}

Then sign in once:

sh
npx @inite/visibility login

That opens a browser, you approve, and the token is stored at ~/.config/inite/mcp.json with owner-only permissions. Authorization code with PKCE over a loopback redirect, the flow RFC 8252 prescribes for a native app. Nothing is written to the repository and no secret ships in the package.

Already have a token (CI, a shared config, a container):

json
{  "mcpServers": {    "inite": {      "command": "npx",      "args": ["-y", "@inite/visibility"],      "env": { "INITE_TOKEN": "…" }    }  }}

INITE_TOKEN wins over the stored file.

Client speaks remote MCP? Skip this package. Point it straight at https://inite.ai/api/mcp/analyzer: every open tool answers without a token, and a member tool answers 401 with WWW-Authenticate naming the protected-resource metadata, which names the authorization server.

Tools

Local — no account:

toolwhat it does
check_ai_access(url)Which AI crawlers robots.txt lets in, separating the ones that fetch a page to answer a live question from the ones that only collect training data. Blocking the first kind is what makes a site invisible; blocking the second costs nothing.
check_identity_files(url)Which of the ten identity files exist — llms.txt, ai.json, identity.json and the rest.
check_page_signals(url)Title, description, canonical, hreflang, and the Schema.org types in the page's JSON-LD.

Remote — open without an account, more with one:

toolwhat it does
check_identity(url)Free and instant: which answer-engine crawlers get in, the identity files, structured data, an identity score out of 100 and what that reading says to fix. No model asked.
visibility_fixes(url)The fix plan, most important first: what to change, why, how many points it should recover, the pages it applies to, and a paste-ready file when there is one. Signed in, built from your latest audit of the site.
compare_sites(url, other)Your site and a competitor's, read the same way, side by side, and who is ahead on each count.
visibility_history(url)How the reading moved: the INITE Atlas's weekly readings for a site it carries, and your own audits.
analyze_site(url)Starts the audit that also asks the answer engines whether they name the site, and returns a run_id. A survey without an account, the teaser on a free plan, the whole audit on a paid one.
get_analysis(run_id)Progress while it runs; the score out of 100 and what to fix first once it finishes.
my_reports()Signed in: your audits, newest first.

Two tools rather than one for the audit, because it is asynchronous. A single tool that blocked for a minute would be torn down by most clients' timeouts.

Commands

inite-visibility            run as an MCP server over stdio (what a client does)inite-visibility login      sign in through the browserinite-visibility whoami     say whether a usable token is present

What this package is

Two halves.

The local checks are real work done here: fetching, parsing, and the robots rules applied properly — most-specific group wins, longest matching rule wins, Allow breaks a tie. They cost nobody anything because your machine does them.

The remote half defines no schemas of its own. It asks inite.ai what it offers and forwards calls there, so that tool list is whatever the service implements today. A local copy would be a second source of truth, and the first thing it would do is drift.

What stays on the server is what costs something or is ours: four answer engines asked whether they name a site, and the weights that turn everything into one number. The local tools report facts; analyze_site reports a score.

Account and allowance

Without an account every open tool answers, under a per-address allowance: the identity check, the fix plan, the comparison and the history, and the audit as a survey, two a day. An account makes the audit its plan's own, exactly as on the website: the teaser on a free plan, the full pipeline - four answer engines asked - on a paid one. Plans are here.

Environment

variablemeaning
INITE_TOKENUse this token instead of the stored one.
INITE_MCP_URLPoint at a different endpoint. Default https://inite.ai/api/mcp/analyzer.
INITE_TOKEN_FILEWhere the token lives. Default ~/.config/inite/mcp.json.
INITE_AUTH_URLAuthorization server. Default https://auth-api.inite.ai.

Namespace

Published to the MCP registry as ai.inite/inite-visibility, a namespace held by proving control of inite.ai — the public half of the key is served at /.well-known/mcp-registry-auth.

Named by the domain rather than the code host on purpose: a service whose whole job is being legible to machines should tell them who it belongs to in its own name.

A note on the command name

npx @inite/visibility resolves because there is exactly one binary in the package. npm looks for a command matching the package name with the scope stripped — visibility — does not find it, and runs the only one there is.

The binary is called inite-visibility rather than visibility on purpose: a scoped package has no business claiming a word that general in your PATH on a global install. The cost is that a second binary would break the line above for every client, so a test pins it at one.

If you are invoking it from a directory that contains this package's own package.json, npm prefers the local copy and finds no linked command. Name it explicitly there:

sh
npx -p @inite/visibility inite-visibility login

Development

sh
npm installnpm run buildnpm test

The tests cover what the bridge can get wrong without saying so: dropping the credential, turning "signed out" into "broken", swallowing an error into a success, and letting a stale file beat the environment.

Contribute with an AI agent

[Open in GitHub Codespaces]

You don't need to be an engineer. Open the repo in your coding agent and say /contribute (Claude Code) — or "read AGENTS.md and help me add …" in any other agent. AGENTS.md holds the rules, the commands CI runs and the idea → PR loop; CONTRIBUTING.md is the short version. Only want to suggest something? /spec-idea, or the Product idea form.

Licence

MIT. The service it talks to is INITE.

來源:README.md,提交 797e761

工具

7

check_identity

Check how machines read a site

Free and instant, no account: read a website the way an AI engine does before it ever answers about it. Returns which answer-engine crawlers robots.txt lets in (retrieval, which decides whether the site can be cited) and which training crawlers it blocks (which costs nothing), the identity files present (llms.txt, ai.json and the rest), whether the homepage carries Organization schema, an identity score out of 100, and the fixes that reading names. No model is asked; for whether the engines actually name the site, run analyze_site.

輸入參數url必填

analyze_site

Audit a site for AI visibility

The AI visibility audit: the identity files, crawler policy, schema graph and page health, then the answer engines asked whether they name the site, scored out of 100. Starts a run and returns its run_id; it takes about a minute, so call get_analysis with that id. Without an account it runs the survey (the audit without its two paid steps), two a day per address; a free account gets the teaser, a paid plan the whole audit, on the account's own allowance.

輸入參數url必填

get_analysis

Read an audit

Read an audit started by analyze_site: progress while it runs, then the score out of 100 and what to fix first. Only the caller who started the run can read it - the account, or for a guest the same address.

輸入參數run_id必填

visibility_fixes

What to fix, in order

The fix plan for a site's AI visibility, most important first: what to change, why it matters for being named in AI answers, how many points of the score it should recover, the pages it applies to, and a paste-ready file or snippet when there is one (llms.txt, robots.txt rules, Organization schema). Free from the identity reading, no account; signed in, it is built from your latest finished audit of that site, which covers the answer engines too.

輸入參數url必填limit

compare_sites

Two sites, read the same way

Your site against a competitor's, read the way an AI engine reads them before it answers: identity score out of 100, which answer-engine crawlers each lets in, the identity files each has (llms.txt, ai.json and the rest), Organization schema, and where each one is ahead. Free and instant, no model asked; counts two identity checks.

輸入參數url必填other必填

visibility_history

How a site's reading moved

How a site's AI visibility reading has moved over time: for a site in the INITE Atlas, its weekly readings (identity score, answer-engine crawlers let in, llms.txt, Organization schema, the top fix each week); signed in, your own audits of it too, with their scores. Free, no model, and no check is spent: it reads what was already measured.

輸入參數url必填

inite_connect

Connect another INITE server

INITE's MCP servers and how to add each to this client: INITE Atlas and INITE Atlas Owners (signed in: add a tool, its card, premium), INITE Visibility and its signed-in door (your audits, a licence), INITE and its signed-in door (your account, Local Start). Call it when the person wants something this server does not do; give `for` to get the one server that does it. Returns the URL, the Claude Code command, Cursor and VS Code install links, and the custom-connector step for claude.ai and ChatGPT.

輸入參數for

版本歷史

2
  1. v2.1.0最新Oct 20, 2026
  2. v1.1.2Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Inite 整合