protogrid

Search / io.github.mcp-dir/busca_google-mcp

Buscador Google

R0· no sign-in

Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar

v0.1.0 · active · repository · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality88good
Trust91of 100
Uptime, 30 days97%
Latency p50118 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "busca_google-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_busca_google"
    }
  }
}
claude mcp add --transport http busca_google-mcp https://api.mcp.ai/p_busca_google
[mcp_servers.busca_google-mcp]
url = "https://api.mcp.ai/p_busca_google"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "busca_google-mcp": {
      "type": "remote",
      "url": "https://api.mcp.ai/p_busca_google",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "busca_google-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_busca_google"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=busca_google-mcp&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLm1jcC5haS9wX2J1c2NhX2dvb2dsZSJ9"
}
{
  "servers": {
    "busca_google-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_busca_google"
    }
  }
}
{
  "mcpServers": {
    "busca_google-mcp": {
      "httpUrl": "https://api.mcp.ai/p_busca_google"
    }
  }
}
extensions:
  "busca_google-mcp":
    enabled: true
    name: "busca_google-mcp"
    type: streamable_http
    uri: "https://api.mcp.ai/p_busca_google"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene93 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • warn
    tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations18 of 18 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 3,290 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

18 tools, about 3,290 tokens to load them all · tool set e96fa0809995 · checked 2026-10-19 10:20 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 91 / 100

provenance80
liveness99
freshness85
hygiene100

+repository +namespace-matches-repo +reachable +uptime-97% ~updated-51d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://api.mcp.ai/p_busca_google streamable-httpnoneyes97%118 ms2025-11-252026-10-19

Tools (18)

authenticateMCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
busca_google_academicoread-onlyBusca artigos no Google Acadêmico com título, autores, publicação, ano e número de citações. Aceita até 100 consultas por chamada.
busca_google_avaliacoesread-onlyLê as avaliações de um estabelecimento no Google: nota, data e texto de cada uma. O identificador vem no campo cid devolvido por busca_google_lugares ou busca_google_mapas, então o caminho natural é achar o negócio e depois ler o que falam dele. Aceita até 100 estabelecimentos por chamada.
busca_google_imagensread-onlyBusca imagens no Google e devolve a URL da imagem, a miniatura, as dimensões e a página de origem. Aceita até 100 consultas por chamada.
busca_google_lugaresread-onlyBusca estabelecimentos no Google com endereço, telefone, site, nota e número de avaliações. É a ferramenta de prospecção local: uma consulta por cidade ou bairro devolve a lista pronta para contato. Aceita até 100 consultas por chamada.
busca_google_mapasread-onlyBusca no Google Maps e devolve o dobro de estabelecimentos por consulta, com coordenadas de latitude e longitude. Use quando precisar de cobertura ou do mapa; para volume, busca_google_lugares custa um terço do preço. Aceita até 100 consultas por chamada.
busca_google_noticiasread-onlyBusca notícias no Google News com título, fonte, data e link. Combine com o parâmetro periodo para monitorar um assunto nas últimas horas ou dias. Aceita até 100 consultas por chamada.
busca_google_paginaread-onlyLê uma página da web e devolve o texto limpo mais os metadados dela. Use depois de uma busca, para abrir os links que interessaram. Custa o dobro de uma busca web por URL. Aceita até 100 URLs por chamada.
busca_google_patentesread-onlyBusca patentes no Google Patents com título, número, depositante e data. Aceita até 100 consultas por chamada.
busca_google_shoppingread-onlyBusca produtos no Google Shopping com preço, loja, nota e imagem. Serve para pesquisa de preço e monitoramento de concorrência. Custa o dobro de uma busca web por consulta. Aceita até 100 consultas por chamada.
busca_google_sugestoesread-onlyDevolve as sugestões de autocompletar do Google para um termo. Serve para descobrir como as pessoas realmente pesquisam um assunto, útil em SEO e pesquisa de mercado. Aceita até 100 termos por chamada.
busca_google_videosread-onlyBusca vídeos no Google com título, canal, duração e link. Aceita até 100 consultas por chamada.
busca_google_webread-onlyBusca na web pelo Google e devolve os resultados orgânicos com título, link e trecho, mais a resposta direta e o painel de conhecimento quando existem. Aceita até 100 consultas por chamada.
connectread-onlyReturns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
marketplaceThe official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
report_bugReport a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
show_versionread-onlyShow the current MCP platform and adapter versions.
toolkit_inforead-onlyReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Schemas: list_tools.

Similar MCP servers

More from io.github.mcp-dir

And 1,107 more from this publisher.

Official server.json
{
  "name": "io.github.mcp-dir/busca_google-mcp",
  "title": "Buscador Google",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.mcp.ai/p_busca_google",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/mcp-dir/busca_google-mcp",
    "source": "github"
  },
  "description": "Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar"
}