Cursor's background agent can use MCP servers to access external tools, but it lacks built-in web search for checking documentation, API changes, or package versions. Adding an MCP search server gives the agent live SERP results it can reference while coding. This tutorial shows how to configure the Scavio MCP server in Cursor's settings, verify the connection, and use search from within the background agent. You will have a Cursor setup that can look up documentation, check API endpoints, and verify package compatibility on demand.
Prerequisites
- Cursor IDE installed (latest version)
- A Scavio API key from scavio.dev
- Basic familiarity with Cursor MCP settings
Walkthrough
Step 1: Open Cursor MCP settings
Navigate to Cursor settings to add a new MCP server configuration.
# Cursor MCP configuration file location:
# macOS: ~/Library/Application Support/Cursor/mcp.json
# Linux: ~/.config/Cursor/mcp.json
# Or configure via Cursor Settings > MCP ServersStep 2: Add the Scavio MCP server
Configure the Scavio MCP endpoint with your API key.
# Add to your Cursor MCP configuration:
# {
# "mcpServers": {
# "scavio": {
# "url": "https://mcp.scavio.dev/mcp",
# "headers": {
# "x-api-key": "YOUR_SCAVIO_API_KEY"
# }
# }
# }
# }Step 3: Verify the connection
Test the MCP server connection by running a search from Cursor's agent.
# In Cursor background agent, ask:
# "Search for the latest Next.js 15 API route documentation"
#
# The agent should use the scavio search tool
# and return results from the webStep 4: Test the API directly
Verify the search API works before relying on the MCP connection.
import os, requests
API_KEY = os.environ["SCAVIO_API_KEY"]
resp = requests.post("https://api.scavio.dev/api/v1/search",
headers={"x-api-key": API_KEY},
json={"platform": "google", "query": "Next.js 15 API routes documentation"})
for r in resp.json().get("organic_results", [])[:3]:
print(f"{r['title']}: {r.get('link','')}")Python Example
import os, requests
API_KEY = os.environ["SCAVIO_API_KEY"]
resp = requests.post("https://api.scavio.dev/api/v1/search",
headers={"x-api-key": API_KEY},
json={"platform": "google", "query": "Next.js 15 API routes docs"})
for r in resp.json().get("organic_results", [])[:5]:
print(r["title"], r.get("link",""))JavaScript Example
const H = {"x-api-key": process.env.SCAVIO_API_KEY, "Content-Type": "application/json"};
async function search(q) {
const r = await fetch("https://api.scavio.dev/api/v1/search", {
method: "POST", headers: H,
body: JSON.stringify({platform: "google", query: q})
});
return (await r.json()).organic_results || [];
}
search("Next.js 15 API routes docs").then(rs =>
rs.slice(0,5).forEach(r => console.log(r.title, r.link))
);Expected Output
A Cursor IDE setup with MCP web search that lets the background agent look up documentation, verify APIs, and search the web without leaving the editor.