Skip to main content
AI/MLjeremylongshore

serpapi-deploy-integration

'Deploy SerpApi-powered search features to production platforms.

Stars
2,267
Source
jeremylongshore/claude-code-plugins-plus-skills
Updated
2026-05-31
Slug
jeremylongshore--claude-code-plugins-plus-skills--serpapi-deploy-integration
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/HEAD/plugins/saas-packs/serpapi-pack/skills/serpapi-deploy-integration/SKILL.md -o .claude/skills/serpapi-deploy-integration.md

Drops the SKILL.md into .claude/skills/serpapi-deploy-integration.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

SerpApi Deploy Integration

Overview

Deploy SerpApi-powered search as a backend API endpoint. Always proxy through your server -- never expose the API key to browsers.

Instructions

Vercel Serverless Function

// api/search.ts
import { getJson } from 'serpapi';

export default async function handler(req: Request) {
  const url = new URL(req.url);
  const q = url.searchParams.get('q');
  if (!q) return new Response('Missing q parameter', { status: 400 });

  const engine = url.searchParams.get('engine') || 'google';
  const num = parseInt(url.searchParams.get('num') || '5');

  const result = await getJson({
    engine, q, num,
    api_key: process.env.SERPAPI_API_KEY,
  });

  return Response.json({
    results: result.organic_results?.slice(0, num) || [],
    answer_box: result.answer_box || null,
    total_results: result.search_information?.total_results,
  });
}
vercel env add SERPAPI_API_KEY production
vercel --prod

Cloud Run with Python

# main.py
from flask import Flask, request, jsonify
import serpapi, os

app = Flask(__name__)
client = serpapi.Client(api_key=os.environ["SERPAPI_API_KEY"])

@app.route("/search")
def search():
    q = request.args.get("q")
    if not q:
        return jsonify({"error": "Missing q parameter"}), 400

    result = client.search(engine="google", q=q, num=5)
    return jsonify({
        "results": result.get("organic_results", [])[:5],
        "answer_box": result.get("answer_box"),
    })
gcloud run deploy search-api \
  --source . --region us-central1 \
  --set-secrets=SERPAPI_API_KEY=serpapi-key:latest \
  --allow-unauthenticated

Health Check

app.get('/health', async (req, res) => {
  const account = await fetch(
    `https://serpapi.com/account.json?api_key=${process.env.SERPAPI_API_KEY}`
  ).then(r => r.json());

  res.json({
    status: account.plan_searches_left > 0 ? 'healthy' : 'credits_exhausted',
    remaining: account.plan_searches_left,
  });
});

Error Handling

Issue Cause Solution
Cold start slow First request initializes Pre-warm with min instances
Credits run out No budget monitoring Add health check with credit count
Key exposed Frontend calling SerpApi directly Always proxy through backend

Resources

Next Steps

For webhook-like patterns, see serpapi-webhooks-events.