adsmart-appSAFE
Gerencie suas campanhas do Google Ads conversando com o Claude. Extensão open source para o Claude Desktop (MCPB), 100% local, com prévia, confirmação e desfazer.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Extensão open-source para o Claude Desktop que conecta o Claude às suas contas do Google Ads. Consulte métricas, analise campanhas e faça alterações com prévia, aprovação e desfazer, tudo em português e rodando no seu computador.
[](LICENSE) [](https://github.com/ZenniTTy/adsmart-app/actions/workflows/ci.yml)
English · Português
[!NOTE] Extensão open source para gerenciar Google Ads pelo Claude Desktop no macOS e no Windows. A versão v0.1.1 está nos releases; o site é adsmart.digital.
O que é a AdSmart
A AdSmart é um servidor MCP (Model Context Protocol) empacotado como extensão do Claude Desktop (.mcpb). Ela dá ao Claude acesso seguro à Google Ads API usando a sua própria conta de serviço do Google Cloud, para que você gerencie campanhas de Google Ads conversando em linguagem natural:
- "Como foram minhas campanhas nos últimos 7 dias?"
- "Quais termos de pesquisa gastaram mais de R$ 50 sem converter este mês?"
- "Quanto de parcela de impressões estou perdendo por orçamento?"
- "Pausa a campanha Black Friday e sobe o orçamento da Institucional para R$ 80/dia."
- "Adiciona 'grátis' e 'curso online' como palavras-chave negativas na campanha Pesquisa."
- "Desfaz a última alteração."
É uma alternativa local e gratuita a ferramentas de automação de Google Ads na nuvem: não há servidor intermediário, assinatura nem coleta de dados.
Por que usar
- 100% local. Roda no seu computador. A chave da conta de serviço nunca sai da sua máquina e nada passa por servidores de terceiros. A extensão só fala com
googleads.googleapis.comeoauth2.googleapis.com. - Sem custo. A Google Ads API é g
c882082b9353OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add adsmart-site --env ADSMART_TEST_TOKEN_FAILS=${ADSMART_TEST_TOKEN_FAILS} -- npx -y adsmart-site{
"mcpServers": {
"adsmart-site": {
"command": "npx",
"args": [
"-y",
"adsmart-site"
],
"env": {
"ADSMART_TEST_TOKEN_FAILS": "${ADSMART_TEST_TOKEN_FAILS}"
}
}
}
}Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
aplicar | read | |
consultar | read | |
desfazer | read | |
diagnostico | read | |
guia_configuracao | read | |
historico | read | |
listar_contas | read | |
preparar_alteracao | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
.bun-version
import { loadConfig } from "../../src/config.js";import { createAdsClient } from "../../src/google/ads-client.js";import { createServiceAccountTokenProvider } from "../../src/google/auth.js";import { createServer } from "../../src/server.js";import { createAdsClient, type HttpFetch } from "../../src/google/ads-client.js";baseUrl: `http://127.0.0.1:${port}/v0`,@biomejs/biome, @commitlint/cli, @commitlint/config-conventional, @types/node, lefthook, typescript
Gates applied: no_behavioural_pass.
c882082b9353full audit observations/trust-audit/mcp-server/zennitty__adsmart-app.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | c882082b9353 | SAFE | B | 89 | first audit |
Questions
What is the adsmart-app MCP server?
Gerencie suas campanhas do Google Ads conversando com o Claude. Extensão open source para o Claude Desktop (MCPB), 100% local, com prévia, confirmação e desfazer.
What tools does adsmart-app expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is adsmart-app safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does adsmart-app need?
It reads ADSMART_TEST_TOKEN_FAILS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (c882082b9353), read on 2026-10-11. The repository is watched and re-audited when it changes.