SERPHouse MCP
About
Enables AI agents and tools to access real-time, high-volume search engine data through a unified Model Context Protocol interface.
Details
- Transport
- SSE
Explore
Setup
Install SERPHouse MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/serphouse/serphouse-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
serphouse_domain_list
List supported search domains. Call this before Yahoo searches — yahoo.com is not valid; use regional domains like uk.yahoo.com from this list.
serphouse_language_list
Get supported language codes for google, bing, or yahoo.
serphouse_location_search
Search Serphouse location ids and location strings for Google or Bing targeting.
serphouse_account_info
Get Serphouse account plan and credit usage.
serphouse_search
Default web search for agents — fast lightweight Google organic results via POST /web-search-lite. Only q is required; gl defaults to US. Use serphouse_google_web only when you need device, gfilter, or num_result. Use serphouse_serp_google_advanced for SEO rankings beyond top 10.
serphouse_google_web_lite
Alias of serphouse_search — fast lightweight Google organic results via POST /web-search-lite. Prefer serphouse_search for general agent queries.
serphouse_google_web
Full Google web search via POST /google-web with device, gfilter, and num_result. Requires loc or loc_id. For general queries use serphouse_search instead.
serphouse_google_image
Run a realtime Google image search via POST /google-image.
serphouse_google_news
Run a realtime Google news search via POST /google-news.
serphouse_google_shop
Run a realtime Google shopping search via POST /google-shop.
serphouse_bing_web
Run a realtime Bing web search via POST /bing-web.
serphouse_bing_image
Run a realtime Bing image search via POST /bing-image.
serphouse_bing_news
Run a realtime Bing news search via POST /bing-news.
serphouse_yahoo_web
Run a realtime Yahoo web search via POST /yahoo-web.
serphouse_yahoo_image
Run a realtime Yahoo image search via POST /yahoo-image.
serphouse_yahoo_news
Run a realtime Yahoo news search via POST /yahoo-news.
serphouse_serp_google_advanced
SEO ranking checks: fetch up to 100 Google results in one request. Use max_pages 1–10 (~10 results per page). For general web search use serphouse_search; use this when rank position beyond the top 10 is needed.
serphouse_google_jobs
Run a realtime Google Jobs search.
serphouse_google_autocomplete
Get realtime localized Google autocomplete suggestions.
serphouse_google_videos
Run a realtime Google Videos search with optional video filters.
serphouse_google_short_videos
Run a realtime Google Short Videos search.
serphouse_google_forums
Run a realtime Google Forums search for discussions and community results.
serphouse_google_local
Run a realtime Google Local search for local business results.
Connect AI assistants to live SERP data, Google verticals, and SEO intelligence — powered bySERPHouse.
Run Google, Bing, and Yahoo searches, resolve locations, and query Jobs, Local, Videos, and more — directly from Cursor, VS Code, Claude Desktop, or any MCP-compatible client. No custom API integration required.
- Why SERPHouse MCP
- Quick Start (Hosted)
- Authentication
- What You Can Ask
- Tools Overview
- Self-Host Locally
- Self-Host with Docker
- Use with Local Llama Models (Ollama)
- Troubleshooting
- Contributing
- License
The fastest path — no build step, no server to maintain.
1.Get your API key from theSERPHouse Dashboard.
2.Add the server to your MCP client config using eitherheader-basedorURL-basedauthentication (seeAuthenticationfor details).
{ "mcpServers": { "serphouse": { "url": "https://mcp.serphouse.com/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
{ "mcpServers": { "serphouse": { "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp" } } }
3.Start chatting. Ask your assistant to search Google, Bing, or Yahoo, look up locations, fetch jobs, or check your account — it will route to the correct tool.
One-click install:Use theInstall in VS CodeorInstall in Cursorbadges above, then replace the placeholder API key with yours.
The server accepts your SERPHouse API key in two ways. Use whichever fits your MCP client.
Tools and resources can be discovered without a key. The API key is required only when calling SERPHouse API tools.
Best when your MCP client supports custom headers. Keeps the key out of URLs and server access logs.
{ "mcpServers": { "serphouse": { "url": "https://mcp.serphouse.com/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
Useful when your client only supports a URL and cannot send custom headers.
{ "mcpServers": { "serphouse": { "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp" } } }
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/YOUR_SERPHouse_API_KEY/mcp" } } }
Note:URL-based auth places the API key in the request path, which may appear in proxy logs or browser history. Prefer the header method when possible.
For SEO teams, agencies, and SaaS marketers who need live search data inside their AI workflow — no dashboards, scripts, or context switching.
The server exposes21 toolsacross five categories. Google and Bing SERP requests require exactly one location field —loc(e.g.Austin,Texas,United States) orloc_id(fromserphouse_location_search). Never send both or omit both on those endpoints. Yahoo SERP tools do not require location.
Run the server on your machine for full control or local development.
git clone https://github.com/SERPHouse/serphouse-mcp.git cd serphouse-mcp npm install npm run build npm start
The server listens onhttp://localhost:3000. MCP endpoints:
- POST /mcp— pass the API key via theSERPHOUSE_APIheader
- POST /{apiKey}/mcp— pass the API key in the URL path
Point your MCP client at the local instance (seeAuthenticationfor both options):
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/YOUR_SERPHouse_API_KEY/mcp" } } }
Health check:GET http://localhost:3000/health
Authentication supports both header and URL path. SeeAuthentication.
Run the MCP server locally in Docker without installing Node.js.
The server runs athttp://localhost:3000/mcp(header auth) orhttp://localhost:3000/{apiKey}/mcp(URL auth).
Connect your MCP client using either method fromAuthentication:
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
{ "mcpServers": { "serphouse": { "url": "http://localhost:3000/YOUR_SERPHouse_API_KEY/mcp" } } }
Hook up your SERPHouse MCP Server to a local Llama model (e.g. Llama 3.1 or 3.2) usingollmcp— an interactive terminal UI client that brings real-time search engine power straight to your local LLM workflow.
ollmcpis a Python client, so install it globally withpip:
The client needs a configuration profile that tells it how to connect to the SERPHouse server and pass your API credentials. Create aconfig.jsonin your working folder using either auth method fromAuthentication:
{ "mcpServers": { "serphouse-mcp": { "url": "https://mcp.serphouse.com/mcp", "headers": { "SERPHOUSE_API": "YOUR_SERPHouse_API_KEY" } } } }
{ "mcpServers": { "serphouse-mcp": { "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp" } } }
ReplaceYOUR_SERPHouse_API_KEYwith your active key from theSERPHouse Dashboard.
Launch the interactive interface, passing your config profile and target model:
ollmcp --servers-json config.json --model llama3.1
- Select your target Llama model from the model list.
- Submit a prompt that needs live web data — e.g."Look up the top Google results for 'best developer tools' using SERPHouse."
- Watch your local Llama model call the SERPHouse tools and turn real-time SERP data into a conversational answer.
The following Ollama models work well with tool use:
- gemma4
- qwen3.5
- lfm2.5-thinking
- llama3.2
- mistral
For a complete list of Ollama models with tool use capabilities, visit the officialOllama modelspage.
For models that can also process images returned by tools, see the Ollamavision modelspage.
Contributions are welcome. Please keep changes focused and match existing code style.
git checkout -b feature/your-feature npm install # make changes npm run typecheck git commit -m "Add your feature" git push origin feature/your-feature
Then open a Pull Request. Update this README if you change setup or configuration.
One MCP server for 160+ live web-data APIs (search, social, e-commerce, real estate, jobs, finance) — clean JSON, free tier.
Get structured search results from Google, Bing, Yandex, DuckDuckGo, and more through one simple API.
Fetch, extract, and process web and API content. Supports resource blocking, authentication, and Google Custom Search.
One API for Search, Crawling, and Sitemaps
Google, Yandex, Baidu, Bing, Duckduckgo, Ecosia Search and URL data Extraction
20+ pay-per-request APIs for AI agents — screenshots, web scraping, PDF, OCR, search, QR codes, translation & more. No API keys needed. Pay with USDC via x402. npm: @pylonapi/mcp
Web search and webpage scraping using the Serper API.
1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection
Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
