Search Console Mcp

io.github.sudomichaelPublished by GitHub account sudomichaelv0.2.2Updated Nov 6, 2026

Google Search Console for any MCP client - 30-second login, no Google Cloud project. Read-only.

VerifiedSTDIODesktop onlyWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Read-only Google Search Console access for MCP clients: query clicks, impressions, CTR and position, compare periods, and check index status.

What you can do
  • List the Search Console properties the signed-in account can access, with exact site URLs
  • Query performance data (clicks, impressions, CTR, average position) by query, page, date, country or device, including Discover traffic
  • Compare two equal-length periods per page or query and get the biggest movers with deltas
  • Inspect index status for one URL or up to 10 URLs in a batch, including canonical and crawl details
  • List submitted sitemaps with status and counts
  • Run built-in SEO analysis prompts such as traffic drop, striking distance and indexing audit
When to use it
Useful when you want to ask an assistant about your own site's search performance in plain language — diagnosing traffic drops, finding queries near page one, or auditing indexing — without building a Google Cloud project or dashboard.
Requirements
Runs locally as an npm package via npx, so Node.js is needed. A one-time browser sign-in with the Google account that has access to the Search Console properties; tokens are stored locally in the user's home directory. Optionally, SEARCH_CONSOLE_MCP_CLIENT_ID and SEARCH_CONSOLE_MCP_CLIENT_SECRET to use your own Google OAuth client.
Before you install
Read-only by design with the webmasters.readonly scope, so it cannot change properties or sitemaps. Google OAuth tokens are stored on disk in the user's home directory; logout deletes them. After login the browser opens the vendor's setup page, and the first analysis of a session includes a labeled note about the vendor's paid service, which can be hidden with SEARCH_CONSOLE_MCP_TIPS=off. Data lags about 2-3 days.

Installation

In SourceWeft

  1. Open Search Console Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

search-console-mcp

Search Console was built for dashboards. This gives you a conversation instead.

Talk to your Google Search Console from Claude, Cursor, or any MCP client.

One sign-in. 30 seconds. No Google Cloud project. No API keys. Tokens never leave your machine.

[npm] [license] [node]

Docs · npm · Report an issue


 Google Search Console          │          ▼  search-console-mcp        ← runs on your machine, read-only          │          ▼  Claude / Cursor / any MCP client          │          ▼  "Why did my traffic drop?"

Most self-hosted Search Console MCP servers make you create a Google Cloud project, enable APIs, and wrangle service-account JSON. This one doesn't:

bash
npx search-console-mcp-server login

Your browser opens, you sign in with Google, done. Tokens are minted by Google directly to your machine and stored only in ~/.search-console-mcp/ — nothing passes through anyone's servers.

This serverTypical self-hosted GSC MCP setup
Setupnpx … login, sign in, done (~30s)Create a Google Cloud project, enable the API, create OAuth credentials, download JSON, point config at it
RuntimeNode — npx, nothing to installPython + uv/venv
Can it modify your site data?Impossible — read-only scope by constructionWrite scopes with destructive ops "disabled by default"
Analyses10 built-in (checkup, traffic drop, traffic decay, striking distance, keyword opportunities, cannibalization, title/CTR rewrite, refresh-vs-new, internal links, indexing audit)Bring your own prompts

What to expect on first run

$ npx search-console-mcp-server loginOpening your browser to sign in with Google…If it doesn't open, visit:
  https://accounts.google.com/o/oauth2/v2/auth?…
Connected. Your Search Console is ready — tokens stored in ~/.search-console-mcp (this machine only).
Want a page change you can review and publish? Percy adds researched drafts, change verification, and follow-through. Separate Google connection; paid plans after the free trial.https://www.getpercy.io/sign-in?source=mcp&workflow=improve-page

The browser opens the setup page only after Google returns valid credentials and they are saved locally. If token exchange or saving fails, it shows an error instead of a success page. No clone or Google Cloud console is required.


What it feels like

You:  Which of my pages are closest to page one?
Claude:  Three real opportunities, by impressions at stake:
  1. /pricing — "scoreboard app pricing" sits at position 11.2 with     2,400 impressions/mo and almost no clicks. One position-group     jump is worth ~90 clicks/mo. The title doesn't contain the     query; start there.
  2. /templates/trivia — position 12.8 on "trivia scoreboard",     1,100 impressions/mo. The page ranks but has no H2 matching     the intent.
  3. /blog/keep-score-online — position 9.4, already page one on     some days. It's cannibalizing with /features — run     cannibalization_check before touching it.

(Illustrative output — shape and numbers are what the tools return from your real data.)

Built-in SEO analysts

Ten ready-made analyses ship as MCP prompts — slash-commands in clients that support them. Each one applies real SEO methodology (thresholds, cause classification, CTR benchmarks) and ends with ranked actions, never a data dump:

PromptWhat you get
seo_checkupTrend vs last month, biggest movers, quick wins — and the top 3 moves scored by impact ÷ effort
traffic_dropWhen the drop started, who lost, and the verdict: rankings, CTR, indexing, demand, or seasonality
traffic_decayPages quietly bleeding clicks month over month — caught and prioritized before they crater
striking_distanceQueries at position 4–20 ranked by estimated click gain, with the one fix per page
keyword_opportunitiesEvery growth lever in one pass: CTR fixes, page-1 pushes, page-2 climbs, emerging demand
cannibalization_checkQueries where your own pages fight each other — the winner, one fix per case, recovery estimate
title_ctr_rewritePages underperforming their position, with rewritten titles + metas grounded in real queries
refresh_vs_newFor any topic: refresh, consolidate, prune, or create new — one verdict from your existing footprint
internal_linksA source → target → anchor link plan, justified by query overlap Google already sees
indexing_auditSitemaps + index status of the pages that matter, triaged by traffic at risk

Setup

1. Sign in (one time):

bash
npx search-console-mcp-server login

2. Add to your MCP client:

Claude Code:

bash
claude mcp add gsc --scope user -- npx -y search-console-mcp-server

Claude Desktop / Cursor / anything else (mcpServers config):

json
{  "mcpServers": {    "gsc": { "command": "npx", "args": ["-y", "search-console-mcp-server"] }  }}

If the app can't find npx (common with nvm), use the absolute path from which npx as command.

3. Ask:

  • "Which of my pages lost the most clicks this month vs last?"
  • "Show my queries sitting at position 8–15 with real impressions — what's closest to page 1?"
  • "Is https://mysite.com/pricing indexed? If not, why?"
  • "How much Google Discover traffic do I get?"

Tools

ToolWhat it does
list_propertiesYour GSC properties (call first — gives exact siteUrl values)
query_search_analyticsClicks / impressions / CTR / position by query, page, date, country, device — filters, pagination, and every traffic source including Google Discover
compare_periodsBiggest movers, computed for you: this period vs the prior one, per-page or per-query deltas, sorted by change
inspect_urlGoogle's index status for a URL: indexed or not, why, chosen canonical, last crawl
inspect_urlsThe same, batched — up to 10 URLs in one call for indexing audits
list_sitemapsSubmitted sitemaps with status

Read-only by construction: the Google scope this tool requests (webmasters.readonly) cannot modify your properties, submit sitemaps, or change anything — not "disabled by default." Impossible.

What a compare_periods call hands your model (the model never does date arithmetic):

json
{ "key": "https://example.com/pricing",  "current":  { "clicks": 1040, "impressions": 20502, "position": 6.4 },  "previous": { "clicks": 1070, "impressions": 17176, "position": 5.8 },  "deltaClicks": -30, "deltaImpressions": 3326, "deltaPosition": 0.6 }

Privacy

  • Read-only Google scope (webmasters.readonly).
  • Tokens live in ~/.search-console-mcp/credentials.json on your machine, chmod 600. npx search-console-mcp-server logout deletes them.
  • No MCP usage telemetry or proxy — Search Console API calls go from your machine directly to Google. After successful login, your browser opens the Percy setup page with only the MCP source and package version in its URL; no credentials, authorization codes, or property data are included.
  • Prefer your own Google Cloud project? Set SEARCH_CONSOLE_MCP_CLIENT_ID / SEARCH_CONSOLE_MCP_CLIENT_SECRET and it uses yours.
  • One short, labeled note about Percy (our paid weekly SEO service) is added to the first analysis result of a session, never repeated. Set SEARCH_CONSOLE_MCP_TIPS=off to hide it. Nothing is sent anywhere either way.

FAQ / Troubleshooting

How can the login work without me creating Google credentials? The CLI ships a Google "Desktop app" OAuth client — the same supported model gcloud and GitHub's CLI use. Your tokens are still minted by Google directly to your machine (PKCE + localhost callback); they never touch our servers. The auth path is in src/auth.ts — read it. Want zero shared anything? Set SEARCH_CONSOLE_MCP_CLIENT_ID / SEARCH_CONSOLE_MCP_CLIENT_SECRET with your own credentials.

Switch Google accounts? npx search-console-mcp-server login again — Google shows the account picker.

"Not signed in" errors in my MCP client? Run the login from the same user account your client runs under; credentials live in ~/.search-console-mcp/.

A property is missing from list_properties. The signed-in Google account needs at least "Restricted" access to it in Search Console.

Why is yesterday missing from the data? Google Search Console data lags ~2–3 days. That's Google, not the tool. History goes back ~16 months.

Revoke access? npx search-console-mcp-server logout deletes local tokens; myaccount.google.com/permissions revokes the grant itself.

Development

bash
git clone https://github.com/sudomichael/search-console-mcpcd search-console-mcp && npm installnpm run dev      # run from sourcenpm run build    # bundle to dist/ (no googleapis dependency)npm test         # mocked login tests; no Google calls or credential writes

The auth path is in src/auth.ts. To verify any privacy claim above, read the source.


Turn the research into a published improvement

The MCP stays free. If you want help preparing one specific page improvement, Percy researches your Search Console evidence, drafts a focused change, and keeps the next action with your saved work. You review and publish it in your own CMS, then verify the change and follow the results.

Percy is a separate paid workspace: 7 days free, no card, then plans from $29/month if you continue. It requires its own Google connection; it does not import local MCP credentials or conversations.


MIT licensed. Issues and PRs welcome. Built by Percy.

Source: README.md at commit 7ac47a3

Tools

6

list_properties

List the Google Search Console properties this account can access. Call this first to get exact siteUrl values (e.g. 'sc-domain:example.com' or 'https://example.com/').

Takes no parameters.

query_search_analytics

Query real Search Console performance data: clicks, impressions, CTR, and average position, grouped by the dimensions you choose. Dates are YYYY-MM-DD (GSC data lags ~2-3 days). Use dimensions like ['query'], ['page'], ['query','page'], or ['date'] for trends.

ParametersendDaterequiredsiteUrlrequiredrowLimitstartRowstartDaterequireddimensionssearchTypepageContainsqueryContains

compare_periods

The biggest-movers analysis, computed for you: this date range vs the prior equal-length range, joined per page (or query) with clicks/impressions/position deltas, sorted by biggest change. Use this for 'what fell/grew', 'this month vs last', and trend diagnosis — it's one call and the math is already done.

ParametersendDaterequiredsiteUrlrequiredrowLimitdimensionstartDaterequiredsearchType

inspect_url

Google's index status for one URL: is it indexed, why not, canonical chosen by Google, last crawl, mobile/rich-result issues.

ParameterssiteUrlrequiredinspectionUrlrequired

inspect_urls

Batch index-status check: up to 10 URLs in one call (per-URL errors reported inline). Use for indexing audits instead of ten single calls.

ParameterssiteUrlrequiredinspectionUrlsrequired

list_sitemaps

List submitted sitemaps for a property, with status and counts.

ParameterssiteUrlrequired

Version history

3
  1. v0.2.2LatestNov 5, 2026
  2. v0.2.1Nov 3, 2026
  3. v0.1.2Sep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts