Run Google Search Console tasks with AI, from one prompt.

ChatGPT and Claude can explain an indexing report; TinyAgent is the AI that opens Search Console and does the checks. Give it a list of URLs and it inspects each one, requests indexing where you allow it, and returns the status as a table.

Free to start. $8 in Wallet funds on us, no card needed.

A real run, step by step

Prompt

Open Google Search Console for my site. Read-only. Give me the last 28 days of clicks, impressions, CTR and average position, and the top 5 pages. Tell me how many pages are not indexed and the top 3 reasons. Inspect my homepage and top 2 pages and tell me if each is on Google.

TinyAgent session view in Google Search Console reading the Performance and Pages reports and running URL Inspection, step list on the left.
TinyAgent auditing a Search Console property read-only: traffic, indexing reasons and URL Inspection, without requesting indexing.

From a list of URLs to an indexing report.

  1. 01

    Give it the property and the URLs

    You
    Name the property, paste the URLs, and say whether it may request indexing.
    TinyAgent
    TinyAgent opens Search Console in a browser signed in through your saved TinyProfiles session.
  2. 02

    Let it work

    You
    Nothing.
    TinyAgent
    TinyAgent runs URL Inspection for each page, reads the status and requests indexing only if your prompt allows it.
  3. 03

    Read the report

    You
    Fix the pages it flags.
    TinyAgent
    TinyAgent returns one row per URL with status, last crawl and issue, plus anything it requested.

Work in Search Console from a chat. Or with the API.

Paste the URLs. TinyAgent checks them.

Install the TinyFish plugin in ChatGPT or Claude, sign in to Google once through TinyProfiles, then name the property and the URLs.

Use TinyFish to open Search Console for example.com. Inspect the 10 blog posts I published this week and tell me which are not indexed and why. Request indexing for those. Do not change anything else.

Set up ChatGPT or Claude

Indexing checks after every publish.

Call TinyAgent with the property and the new URLs whenever you publish, and get the indexing status back as JSON.

Inspect a URL in Search Console from one call:

from tinyfish import TinyFish, EventType, RunStatus

client = TinyFish()

with client.agent.stream(
    url="https://search.google.com/search-console",
    goal="""Open the Search Console property for https://www.example.com. Run URL Inspection for https://www.example.com/blog/new-post. Return JSON with on_google (yes or no), coverage_status, last_crawl and any issue. Do not request indexing or change settings.""",
    use_profile=True,
) as stream:
    for event in stream:
        if event.type == EventType.COMPLETE and event.status == RunStatus.COMPLETED:
            print("Result:", event.result_json)

Runs are billed at $0.016 per agent step.Read the docs

What people use it for.

These are the Search Console jobs people give TinyAgent most often. Each runs in your own account, read-only unless your prompt allows a change.

For content teams

URL inspection in bulk

Paste the pages you published this week. TinyAgent inspects each one and tells you which are on Google, which are not, and the reason Search Console gives, such as “Crawled - currently not indexed”.

Try

Inspect these 20 URLs and list any that are not on Google, with the reason.

You get: One row per URL with on Google, coverage status and last crawl.

See TinyAgent

For site owners

Indexing requests

After a launch or a fix, TinyAgent requests indexing for the pages you name and leaves the rest alone. Google limits requests each day, so put the pages that matter most first.

Try

Request indexing for the 3 pages I updated today. Skip any page that is already indexed.

You get: The pages it requested, and any request Google rejected.

See TinyAgent

For agencies

Property setup

Onboarding a new client? TinyAgent opens, adds or verifies properties across the accounts you manage, so setup does not wait for someone to click through each one.

Try

Add https://client.com as a URL-prefix property and tell me which verification methods it offers.

You get: Property status and any verification steps still open.

See TinyAgent

For SEO specialists

Sitemaps and reports

Submit a sitemap, check that Google read it, and pull the numbers you report on: clicks, impressions, CTR, average position and pages not indexed.

Try

Submit /sitemap.xml, then give me the last 28 days of clicks and impressions and the top 3 reasons pages are not indexed.

You get: Sitemap status, discovered pages and a short report.

See TinyAgent
TinyFish is rated 4.4 out of 5 on G2 - Users Love Us badge

Verified on G2

4.4 out of 5 on G2

  • TinyFish is the one layer I actually keep in the stack when I need live web, not another chatbot pretending it can browse. Search, Fetch, Browser, and Agent sit under one API, so I am not wiring Exa for search, Firecrawl for markdown, and Apify for the messy pages.
    Otman M.Deployment Strategist for AI adoption - ConsultingRead on G2 ↗
  • It is super fast! After onboarding it was very easy to get setup. The starter credits that were given were plenty and each search and fetch were free while agent mode provided a good bang for your buck.
    Verified User in Market ResearchRead on G2 ↗
  • I use TinyFish for hackathons and side projects to scrape websites and provide LLMs with precise context, and I love its speed, accuracy, and the fact that it's fast, cheap, and good. It can return information quickly and accurately from links inside websites or from specific links.
    Verified UserRead on G2 ↗
  • What I like most about TinyFish is how well it handles web-based sources that are hard to reach through conventional APIs.
    deepti b.Founder - Health, Wellness and FitnessRead on G2 ↗
  • The configuration is very simple and it supports MCP, making it basically ready to use out of the box.
    David W.Writer & Editor - Fund-RaisingRead on G2 ↗
  • TinyFish is the page-scrape layer I actually trust after a search API. I run Tavily for broad hits, then TinyFish run-sse against a specific URL with a goal — Gensyn docs, DoraHacks briefs, GitHub orgs, hackathon portals — and it returns extractable text instead of “10 blue links.”
    Henry M.Community Associate - Computer SoftwareRead on G2 ↗
  • I hand it a URL and get back clean Markdown instead of a wall of nav bars, cookie banners and ads, which cuts my token cost on every LLM call downstream. Search and Fetch being free is genuinely rare — everyone else meters exactly this.
    Alessio B.Web Developer - InternetRead on G2 ↗
  • TinyFish has become my default web layer inside Claude Code and OpenCode. The MCP connection was easy to set up, and I was running searches and fetches within minutes.
    Kartik S.Founder - InternetRead on G2 ↗
  • The standout feature of TinyFish is its unified, production-ready web agent architecture that replaces fragile scraping scripts with resilient, human-like browser navigation and multi-step workflow execution through a single API
    Ranganath D.Sr Manager - Airlines/AviationRead on G2 ↗
  • Tinyfish is a highly effective tool for agent search and fetch functions. It’s also free
    Verified User in InternetRead on G2 ↗

Questions, answered.

Give TinyAgent your next indexing check.

Free to start. $8 in Wallet funds on us, no card needed.