google-search
Skill0 starsChanged 40 days agoMITView on GitHub
Get Google results as JSON through the ScrapingBot API - web results, images, videos, news, shopping, local places, Google Maps listings and place reviews, for any country and language. Use when the user wants search results, SERP data, local businesses or Google Maps reviews. Requires SCRAPINGBOT_API_KEY.
- Reads credentials
- Sends data out
12 other projects use a version of this.
Adopted by
Most recently taken up by
- daanielcruz/gsearch-mcptheir own version, first seen Nov 1, 2026
- rocosen/flashdata-mcptheir own version, first seen Oct 17, 2026
- team-attention/hoyeontheir own version, first seen Oct 8, 2026
- AceDataCloud/Skillstheir own version, first seen Oct 6, 2026
- longlannet/google-searchtheir own version, first seen Oct 5, 2026
- nc9/skillstheir own version, first seen Sep 19, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- team-attention/hoyeon★ 173same name
- aiagenta2z/onekey-gateway★ 52same name
- johnqtcg/awesome-skills★ 30same name
- AceDataCloud/Skills★ 17same name
- botlearn-ai/botlearn-skills★ 9same name
- daanielcruz/gsearch-mcp★ 4same name
- KirillTrubitsyn/kirilltrubitsyn-claude-skills★ 4same name
- nc9/skills★ 4same name
- austenstone/.copilot★ 0same name
- longlannet/google-search★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- amazon-productsSkill
- instagram-dataSkill
- tiktok-dataSkill
- web-scrapingSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 52
Every response: searchParameters (your query echoed), creditsUsed.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Google results with ScrapingBot
POST https://scrapingbot.io/api/v1/google, headers x-api-key: $SCRAPINGBOT_API_KEY and Content-Type: application/json.
Body: {"endpoint": "<endpoint>", "params": {...}}. 10 credits per call, charged only on success. Timeout 15 s.
Endpoints
| endpoint | Use for | Required | Results field |
/search | Web results | q | organic, peopleAlsoAsk, relatedSearches |
/images | Images | q | images |
/videos | Videos | q | videos |
/news | News | q | news |
/shopping | Products, prices, stores | q | shopping |
/places | Local businesses | q | places |
/maps | Maps listings, or one place by ID | q, or cid/placeId/fid | places, ll |
/reviews | Reviews of a place | cid, fid or placeId | reviews, nextPageToken |
Params
q: query;site:, quotes and-work as on Google.glcountry (us,gb,de),hllanguage (en,es). Use these for market targeting;locationis passed through but city-level targeting is not reliable.num(Google returns at most 10 per page),page(from 1),start(offset).tbs: time filterqdr:h|d|w|m|y.autocorrect,safe(booleans)./places,/maps:llviewport like@30.27,-97.74,12z./reviews:sortBy=mostRelevant(default),newest,highestRating,lowestRating;nextPageTokenfor the next page (~20 reviews per page).
Workflow for reviews: /places or /maps with q → take cid (or placeId) from a result → /reviews.
Example
curl -X POST "https://scrapingbot.io/api/v1/google" \
-H "x-api-key: $SCRAPINGBOT_API_KEY" -H "Content-Type: application/json" \
-d '{"endpoint": "/search", "params": {"q": "best espresso machine", "gl": "us"}}'Fields worth reading
organic[]:position,title,link,snippet, sometimesdate.images[]:title,imageUrl,imageWidth,imageHeight,thumbnailUrl,source,link.videos[]:title,link,channel,duration,date,source.news[]:title,link,source,date.shopping[]:title,price,source(store),rating,ratingCount,link.places[]:title,address,category,rating,ratingCount,website,latitude,longitude,cid;/mapsaddsphoneNumber,openingHours,placeId,fid.reviews[]:rating,snippet,date,isoDate,likes.- Every response:
searchParameters(your query echoed),creditsUsed.
Errors
Errors are {"success": false, "error": "..."} and are never charged.
400: missingq(or place ID for/reviews). Fix and resend.401bad key;402not enough credits (tell the user);429concurrency limit (free plan allows 1 request at a time; wait and retry).408/5xx: temporary; retry with backoff.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.