Ubersuggest MCP
A standalone MCP server for Ubersuggest that runs entirely locally using SQLite and Playwright, providing tools to query subscription status, projects, domain overview, keyword research, site audit, and more.
README
Ubersuggest MCP - Standalone Node.js Runner
Implementasi standalone Model Context Protocol (MCP) server untuk Ubersuggest yang berjalan sepenuhnya di komputer lokal menggunakan database SQLite (node:sqlite) dan Playwright lokal, tanpa dependensi cloud.
Fitur Utama
- Zero Cloud Infrastructure: Didesain sepenuhnya untuk dijalankan secara lokal di PC Anda.
- Fast Local Caching: Data Site Audit disimpan dalam cache SQLite lokal selama 24 jam. Panggilan berulang selesai dalam < 10ms.
- Auto-Formatting: Menyajikan data teknis audit dalam format Markdown ringkas yang ramah terhadap LLM/klien MCP.
- Playwright Reconnect: Otomatis memperbarui session/cookie Ubersuggest Anda menggunakan browser Playwright lokal.
Cara Install (One-Line Setup)
Anda dapat menginstal dan mengonfigurasikan server MCP ini secara otomatis langsung dari GitHub menggunakan satu baris perintah berikut:
npx github:muizzahabibi/ubersuggest-mcp-node
Perintah ini akan secara otomatis:
- Meminta lokasi folder instalasi permanen di komputer Anda (default:
~/ubersuggest-mcp-node). - Mengkloning repositori ini secara otomatis.
- Memasang dependensi Node.js & browser Playwright (Chromium).
- Melakukan build TypeScript.
- Membuka wizard interaktif untuk mendaftarkan server ke klien MCP pilihan Anda (Claude Desktop, Cursor, Claude Code CLI, Codex CLI, Antigravity IDE/CLI, atau semuanya!).
Jika Anda sudah mengkloning repositori ini secara manual, Anda bisa menjalankan konfigurasi interaktif langsung dari dalam folder proyek dengan perintah:
npm install && npx playwright install chromium && npm run build && npm run setup
Panduan Penyetelan Manual
1. Claude Desktop
Penyetelan manual pada berkas konfigurasi Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"ubersuggest-node": {
"command": "node",
"args": [
"--experimental-sqlite",
"--env-file=/PATH/TO/ubersuggest-mcp-node/.env",
"/PATH/TO/ubersuggest-mcp-node/dist/server.js",
"--stdio"
]
}
}
}
(Ganti /PATH/TO/ dengan path absolut direktori proyek ini).
2. Cursor
- Buka Cursor Settings -> Features -> MCP.
- Klik + Add New MCP Server.
- Isi parameter berikut:
- Name:
ubersuggest-node - Type:
stdio - Command:
node - Arguments:
--experimental-sqlite --env-file="/PATH/TO/ubersuggest-mcp-node/.env" "/PATH/TO/ubersuggest-mcp-node/dist/server.js" --stdio
- Name:
- Klik Save dan restart Cursor.
3. Codex CLI
Wizard npm run setup dapat mengonfigurasi Codex otomatis. Jika ingin manual, tambahkan blok berikut ke ~/.codex/config.toml:
[mcp_servers.ubersuggest_node]
enabled = true
command = "node"
args = ["--experimental-sqlite", "--env-file=/PATH/TO/ubersuggest-mcp-node/.env", "/PATH/TO/ubersuggest-mcp-node/dist/server.js", "--stdio"]
Gunakan nama ubersuggest_node agar bisa berjalan berdampingan dengan MCP Ubersuggest HTTP/remote lain.
4. Antigravity IDE/CLI
Wizard npm run setup dapat mengonfigurasi Antigravity otomatis. Jika ingin manual, tambahkan blok berikut ke ~/.gemini/config/mcp_config.json:
{
"mcpServers": {
"ubersuggest_node": {
"command": "node",
"args": [
"--experimental-sqlite",
"--env-file=/PATH/TO/ubersuggest-mcp-node/.env",
"/PATH/TO/ubersuggest-mcp-node/dist/server.js",
"--stdio"
]
}
}
}
Untuk config per-project Antigravity, gunakan isi yang sama di .agents/mcp_config.json.
Menghubungkan Akun Ubersuggest (Penting)
Sebelum MCP dapat digunakan, Anda harus mengisi sesi login Ubersuggest Anda ke database lokal.
- Jalankan API server lokal:
npm run dev - Buka browser dan akses halaman panduan lokal:
http://127.0.0.1:8787/guide - Lakukan login menggunakan akun MCP Anda (kredensial default: username
admin, passwordadmin-secure-password-123). - Ikuti instruksi di layar untuk menempelkan Cookies browser Anda dari situs app.neilpatel.com. Sesi akan disimpan di SQLite lokal (
ubersuggest.db) dengan enkripsi aman. - Selesai! Matikan server API (
Ctrl + C) dan jalankan MCP client Anda.
Daftar Tools MCP yang Tersedia
ubersuggest_subscription— Mengambil status langganan Ubersuggest Anda.ubersuggest_projects— Mengambil daftar proyek website yang dipantau di akun Anda.ubersuggest_domain_overview— Mengambil metrik lalu lintas (traffic), organic keywords, backlinks, dan SEO score domain tertentu.ubersuggest_domain_top_pages— Mengambil halaman dengan kunjungan tertinggi dari suatu domain.ubersuggest_traffic_estimation— Mengambil riwayat estimasi traffic bulanan.ubersuggest_keyword_research— Melakukan riset ide kata kunci (volume, SEO difficulty, CPC, paid difficulty).ubersuggest_seo_opportunities— Mengambil daftar peluang perbaikan SEO spesifik.ubersuggest_site_audit— Melakukan technical audit website (Core Web Vitals + Crawl Issues).ubersuggest_auth_reconnect— Melakukan penyambungan ulang sesi Ubersuggest.ubersuggest_auth_logout— Logout sesi Ubersuggest dari database lokal.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.