Context7
Up-to-date docs for AI agents
Descripción del creador (original en inglés)
How ChatGPT, Claude, Gemini and Perplexity read a site: free check, fix plan, compare, history.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
INITE_TOKEN, AuthorizationLos valores marcados como secretos son llaves de tu cuenta. Nunca los compartas ni los pegues en un chat.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Esta dirección necesita una clave en un header de la solicitud, y el menú para agregar conectores no puede ponerla. Usa Claude Code, Cursor o VS Code.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"inite-visibility": {
"command": "npx",
"args": [
"-y",
"@inite/visibility"
],
"env": {
"INITE_TOKEN": "your-value"
}
}
}
}Ejecuta esto en tu terminal
claude mcp add --transport http inite-visibility https://inite.ai/api/mcp/analyzer --header 'Authorization: your-value'claude mcp add inite-visibility --env INITE_TOKEN=your-value -- npx -y @inite/visibilityCompleta los valores vacíos antes de ejecutarlo.
Pégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"inite-visibility": {
"url": "https://inite.ai/api/mcp/analyzer",
"headers": {
"Authorization": "your-value"
}
}
}
}Pégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"inite-visibility": {
"command": "npx",
"args": [
"-y",
"@inite/visibility"
],
"env": {
"INITE_TOKEN": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"inite-visibility": {
"type": "http",
"url": "https://inite.ai/api/mcp/analyzer",
"headers": {
"Authorization": "your-value"
}
}
}
}Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"inite-visibility": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@inite/visibility"
],
"env": {
"INITE_TOKEN": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Esta dirección necesita una clave en un header de la solicitud, y el menú para agregar conectores no puede ponerla. Usa Claude Code, Cursor o VS Code.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Authorization secreto HTTP headerEsta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Todavía no hemos leído la lista de herramientas de este servidor; revisamos los endpoints por turnos.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 6 nov 2026
El nombre en el registro se verificó con el dominio inite.ai (el registro comprueba quién es dueño del dominio)
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; leemos la lista de herramientas cuando revisamos el endpoint
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
Debes completar: INITE_TOKEN, Authorization
Funciona de las dos formas: instálalo en tu computadora o conéctate a la versión en la nube.
El repo de GitHub cambió por última vez –, y la última versión (2.1.0) llegó al registro hace 17 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. Se conecta por URL, así que también funcionan las apps que aceptan servidores MCP remotos, como ChatGPT en modo desarrollador.
En la misma categoría: Context7, Codebase Memory, Exa
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
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.
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")
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.
Claude Desktop, Cursor, or any client that launches a stdio server:
{
"mcpServers": { "inite": { "command": "npx", "args": ["-y", "@inite/visibility"] } } }
Then sign in once:
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):
{
"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.
Local — no account:
| tool | what 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:
| tool | what 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.
inite-visibility run as an MCP server over stdio (what a client does)
inite-visibility login sign in through the browser inite-visibility whoami say whether a usable token is present
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.
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.
| variable | meaning |
|---|---|
INITE_TOKEN | Use this token instead of the stored one. |
INITE_MCP_URL | Point at a different endpoint. Default https://inite.ai/api/mcp/analyzer. |
INITE_TOKEN_FILE | Where the token lives. Default ~/.config/inite/mcp.json. |
INITE_AUTH_URL | Authorization server. Default https://auth-api.inite.ai. |
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.
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:
npx -p @inite/visibility inite-visibility login
npm install
npm run build npm 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.
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.
MIT. The service it talks to is INITE.