Google Search Console MCP: No-Code SetupA Google Search Console MCP server lets an AI assistant like Claude or ChatGPT read your Search Console data through the Model Context Protocol (MCP). You ask in plain language, and the assistant calls Google’s Search Console API for clicks, impressions, CTR, positions, URL inspection and sitemaps.
https://mcp.portermetrics.com/mcp into Claude, ChatGPT or Cursor and sign in with Google. Full stepsPorter’s Google Search Console MCP connects your properties to Claude, ChatGPT and any MCP client through one hosted server URL. Ask in plain language and the answer comes from Google’s Search Console API, live. Porter covers four kinds of SEO work: reports, research, audits and management.
Demo data, from a fictional property. Prompt: “List queries from the last 90 days ending 3 days ago with Average Position between 5 and 15 and at least 5,000 Impressions, with the page that ranks for each.”
| Query | Page | Impressions | Average Position | Clicks | CTR |
|---|---|---|---|---|---|
| running shoes for flat feet | /guides/flat-feet-shoes/ | 18,400 | 7.2 | 412 | 2.2% |
| trail running shoes women | /trail/womens/ | 9,650 | 8.9 | 141 | 1.5% |
| best marathon shoes 2026 | /guides/marathon-shoes/ | 22,100 | 11.4 | 198 | 0.9% |
| waterproof running shoes | /collections/waterproof/ | 6,120 | 6.1 | 190 | 3.1% |
Claude then drafts a new title and meta description for each page, starting with the one closest to page one.
Porter’s Search Console MCP reads Google’s Search Console API for every property your Google account can open. The same server URL works in each AI client below, and the same connection feeds Porter’s other destinations.
Only one AI app?
27 fields: 5 metrics and 22 dimensions.
Metrics: Clicks · Impressions · CTR · Average Position
Dimensions: Query · Page URL · Country · Device · Search Appearance · Search Type (Web, Image, Video, News, Discover, Google News) · Date · Week · Month · Quarter · Year
Read actions: list properties (site_list) · query search performance (searchanalytics_query) · inspect a URL (urlinspection_inspect) · list sitemaps (sitemap_list)
Write actions (each asks you first): submit a sitemap (sitemap_submit) · remove a sitemap (sitemap_delete)
Not available: indexing requests, user management and site verification stay in Search Console.
Filters: equals, contains, not contains and regex (include or exclude) on Query, Page URL, Country, Device and Search Appearance
Rows and freshness: up to 25,000 rows per request, past the 1,000-row table in Search Console. Google’s data runs about 2 to 3 days behind: ask for final data only, or include the latest partial days.
Pair Search Console with the Google Analytics 4 MCP, the Google Ads MCP or the Google Business Profile MCP. One Porter connection covers all of them, or see every MCP server.
The same Search Console connection also sends data to Data Studio (formerly Looker Studio), BigQuery and Google Sheets, at no extra cost.
Porter’s Search Console MCP reads your properties without changing them. Reports, research and URL inspection are reads. Sitemap submissions and removals are the only changes, and nothing is sent until you approve it in the chat.
Queries, pages, clicks and URL inspection never change your property. Changes happen only when you ask for one and approve it.
You sign in with Google in Porter. Porter works through Google’s Search Console API, with the scopes Google defines in its Search Console API authorization guide.
Porter sees only the properties your Google account can open, with the rights Google gives that account, as Search Console users and permissions explains.
Removing a sitemap can’t be undone, so the chat flags it before asking. To bring it back, submit the same URL again.
Disconnect the property in Porter whenever you want. Access lives in your Google connection, not in a key file on someone’s machine.
Paste this server URL into your AI app, then sign in with Google:
First, create a free Porter account and connect Google Search Console: Create → pick your AI app as the destination → Google Search Console → sign in with Google → select your properties.
Before you connect: sign in to Search Console with the same Google account and check that it opens each property’s Performance report. A Domain property (sc-domain:example.com) and a URL-prefix property (https://www.example.com/) are separate, so pick the one your team reports on. If a property is missing, ask its owner to add you, per Google’s property permissions guide.
Porter and paste https://mcp.portermetrics.com/mcp.On Team and Enterprise plans, an owner adds the connector first. Anthropic’s custom connector guide covers the same steps.
ChatGPT has two routes to the same data. The Porter Metrics app in ChatGPT’s app directory works on any plan with apps. The Porter MCP gets every new tool the day Porter ships it, on Business, Enterprise and Edu workspaces.
Porter Metrics app: in ChatGPT, open Apps, search “Porter Metrics”, click Connect and sign in with the Google account you use in Porter.
Porter MCP:
Porter and paste https://mcp.portermetrics.com/mcp under Connection.Pro accounts can add it with read access only, per OpenAI’s custom MCP server guide.
Pick your coding agent. Each one uses the same server URL and a Google sign-in, so no API key or credentials file sits in a config.
/plugin marketplace add portermetrics/porter
/plugin install porter-metrics@portermetricsclaude mcp add --transport http porter https://mcp.portermetrics.com/mcp/mcp shows porter as connected. Ask: “Which Google Search Console accounts can you see?”mcp.json.{
"mcpServers": {
"porter": { "url": "https://mcp.portermetrics.com/mcp" }
}
}Ctrl/Cmd+Shift+P) and run MCP: Add Server → HTTP.https://mcp.portermetrics.com/mcp, name it porter and choose Global. Or add it to .vscode/mcp.json:{
"servers": {
"porter": { "type": "http", "url": "https://mcp.portermetrics.com/mcp" }
}
}codex mcp add porter --url https://mcp.portermetrics.com/mcpcodex mcp login portercodex mcp list shows porter as logged in. Start codex. Ask: “Which Google Search Console accounts can you see?”The same URL works in Windsurf, Cline, Zed and any client that supports remote MCP servers over HTTP.
Porter’s skill teaches Claude which Porter tools to call for each SEO task, so answers need fewer retries. In claude.ai, download https://mcp.portermetrics.com/skill.zip and upload it in Settings → Capabilities → Skills. In Claude Code, Porter’s plugin adds it for you, and other agents can run npx skills add portermetrics/porter.
Paste this into a new chat. It only reads data.
Use Porter only. List my Google Search Console properties and my access level on each. For the first property, show clicks, impressions, CTR and average position for the 7 days ending 3 days ago, grouped by page, top 5 rows. Say so if a property returns no data.Copy a prompt into Claude or ChatGPT, then swap in your brand terms, thresholds and dates. End date ranges 3 days ago, when Google marks the data final.
Porter’s Search Console MCP fits SEO teams who check rankings every week and want the answer without exporting a table.
Google has no official Search Console MCP as of November 2026, so the choice is a hosted server like Porter’s or an open-source server you run, like mcp-gsc on GitHub. Both read Google’s Search Console API. Here is where they differ.
| Porter | Open-source (mcp-gsc) | |
|---|---|---|
| Setup | Google sign-in, then one URL in your AI app | Python 3.11+, a Google Cloud project with the Search Console API, an OAuth client or service account |
| Steps before your first question | 3: connect Search Console in Porter, paste the URL, sign in with Google | 5 in Google Cloud (project, Search Console API, credentials, consent screen, key download), then a local install and config |
| Credential files on your computer | None | An OAuth client secrets or service-account JSON, plus a saved token |
| Hosting | Hosted at mcp.portermetrics.com/mcp | Runs on your own machine |
| Several properties in one prompt | Yes, every connected property at once | One configuration per setup |
| Other sources in the same chat | GA4, Google Ads and 30+ more | Search Console only |
| Competitor SEO research | Keywords, search results and competitor pages, with automation credits | No |
| Live dashboards and scheduled reports | Yes | No |
| Data Studio, BigQuery, Google Sheets | Same connection | No |
| Price | Included in every Porter plan, free plan too | Free, MIT license |
The mcp-gsc column follows its GitHub README (as of November 2026). Pick mcp-gsc to run the code yourself for one property. Pick Porter for every property, every channel and no setup.
Connector platforms such as OOMOL and Composio also host a Search Console MCP. They’re built for developers wiring many apps into agents. Porter is built for SEO and marketing reporting:
One prompt answers for all your connected sites and clients, not one property per setup.
GA4, Google Tag Manager, Google Ads, Meta Ads and Shopify, blended in one answer.
Keywords, live search results and competitor pages, next to your own Search Console numbers.
Live dashboards, scheduled email reports, and the same data in Data Studio, BigQuery and Google Sheets.
One URL and a Google sign-in. No API key, team header or service-account file in a config.
A remote MCP URL, plus an approved app in ChatGPT’s app directory.
The Google Search Console MCP is included in every Porter plan, the free-forever plan too. Reporting is billed per connected account, and each Search Console site counts as one account.
Reporting price for connected accounts, in USD. AI chats, queries and dashboards are unlimited. Annual billing is 10 months for 12.
The more accounts you connect, the lower the price per account. See the full calculator on Porter pricing.
No. As of November 2026, Search Console isn't on Google's list of products with MCP servers, and Google's open-source MCP covers Analytics, not Search Console. You connect Search Console to an AI app through a hosted server like Porter's, an open-source server like mcp-gsc, or your own API code.
Yes, several open-source ones. The most used is mcp-gsc, a Python server with 20 tools. Each needs your own Google Cloud project and credentials. Porter's is hosted, so there's nothing to install.
Porter's Google Search Console MCP server URL is https://mcp.portermetrics.com/mcp. Paste it into Claude, ChatGPT or another MCP client, then sign in with Google and pick your properties.
Yes. GSC is the short name for Google Search Console, so a GSC MCP is a Search Console MCP server.
Yes. Search Console's own tables stop at 1,000 rows (Google's 1,000-row table limit), while Google's API returns up to 25,000 rows per request.
Google keeps 16 months of Search Console data. Porter's paid plans read whatever the API returns; the free plan keeps up to 30 days (15 days in AI chats), and the 14-day trial has no history limit.
Search Console days follow Pacific time, and the newest days stay empty until Google marks them final. With Page URL in the question, Google counts each URL shown, so page totals run higher than site totals.
Your Google account needs access to that exact property in Search Console. If Porter shows it as unverified, ask the property owner to add you as a user, or connect the Google account that already has access. A Domain property and its URL-prefix version need separate access.
Check the property, the date range, the search type (Web, Image, News) and any filters. An empty result isn't a permission error, and days newer than about 3 days ago may not be final yet.
Connect Search Console to Claude, ChatGPT or any MCP client and run your first SEO report today.
Start free: unlimited connected accounts, no credit card.
