About CrustAPI
CrustAPI is an MCP server for AI agents that provides live Google search surfaces and public LinkedIn data through CrustAPI endpoints. It also retrieves webpage content and Google business reviews as structured JSON.
Key features
- 01Google search across web, maps, news, and more
- 02Public LinkedIn profiles, companies, posts, and jobs
- 03Scrape webpages into text, metadata, and JSON-LD
- 04Retrieve Google business reviews
- 05Structured JSON responses
Use cases
- 01Find local businesses and map results
- 02Collect current news or web search results
- 03Review public LinkedIn people and company data
- 04Extract webpage content for RAG
- 05Retrieve business reviews
MCP support
Exposes search, webpage scraping, review, and LinkedIn tools to MCP clients. It calls CrustAPI hosted endpoints and requires a CrustAPI API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y crustapi-mcpCRUSTAPI_API_KEYSecretYour CrustAPI key from crustapi.com/app (free tier: 3,000 credits/month)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| q | string | Yes | The search query, e.g. 'best crm software' or 'dentists in miami'. |
| gl | string | No | Country code (us, gb, de, ...). Default us. Not used by maps. |
| hl | string | No | Language code (en, es, ...). Default en. |
| page | integer | No | Result page (default 1). |
| type | enum | Yes | Which Google surface to query.web | maps | places | news | shopping | images | videos | scholar | patents | autocomplete |
| limit | integer | No | type=maps only: how many businesses to return (default 20; 1 credit each). |
| location | string | No | City/region for web and maps, e.g. 'Austin, TX'. |
Details
From the project READMECrustAPI MCP server
Give any MCP client (Claude Desktop, Cursor, Cline, Claude Code) live Google and public LinkedIn
data. It calls the hosted CrustAPI /v1/search and /v1/linkedin endpoints.
Tools
searchcovers the whole Google menu behind one tool. Pick the surface withtype:web,maps,places,news,shopping,images,videos,scholar,patents,autocomplete.scrape_webpagefetches any URL as clean text + metadata + JSON-LD (RAG-ready).get_reviewspulls Google reviews for a business (byplaceId/cid/fidor a name query).linkedincovers public LinkedIn data behind one tool. Pick the surface withtype:profile,company,posts,jobs, orsearch(people search). Addenrich=trueon people search to get each person's full profile.
You only pay for successful results; empty results are free. Get a free key (3,000 credits/month, no card) at https://crustapi.com.
Installation
Recommended: npx, nothing to install.
Add this to your MCP client config (e.g. Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"crustapi": {
"command": "npx",
"args": ["-y", "crustapi-mcp"],
"env": { "CRUSTAPI_API_KEY": "key_live_xxxx" }
}
}
}
Restart the client and the four tools appear. Requires Node 18+.
From source
npm install
{
"mcpServers": {
"crustapi": {
"command": "node",
"args": ["/absolute/path/to/crustapi-mcp/server.mjs"],
"env": { "CRUSTAPI_API_KEY": "key_live_xxxx" }
}
}
}
Env
| var | purpose |
|---|---|
CRUSTAPI_API_KEY | your CrustAPI key, sent as x-api-key (required) |
CRUSTAPI_BASE_URL | defaults to https://crustapi.com; point at a local URL for testing |
Usage
search(type="web", q="best serp api 2026")search(type="maps", q="dentists", location="Miami, FL", limit=20)search(type="news", q="openai")scrape_webpage(url="https://example.com/pricing", includeMarkdown=true)get_reviews(q="Blue Bottle Coffee", sortBy="newest")linkedin(type="profile", url="https://www.linkedin.com/in/williamhgates")linkedin(type="search", keywords="head of growth fintech", enrich=true)
Every response is stable, structured JSON.
Test it
CRUSTAPI_API_KEY=key_live_xxxx node test-client.mjs
This spawns the server over stdio, lists the tools, and calls one.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.