Skip to main content
Glama
SearchLink Lite

SearchLink Lite

SearchLink Lite

HOL Guard Scanner Indexed on TensorBlock MCP Index

Google Search Console inside Claude, Cursor and any MCP client. Runs on your machine, read-only, free (MIT).

Ask things like:

  • "How did example.com do on Google in the last 28 days?"

  • "Which pages lost the most clicks?"

  • "Which queries get impressions but no clicks?"

  • "Is https://example.com/pricing indexed?"

Tools

Tool

What it answers

list_sites

Which sites are in your Search Console

site_overview

Clicks, impressions, CTR, position vs the previous period, biggest drops and gains, up to 3 things to do now

search_performance

Any breakdown by query, page, country, device or date, with filters and period comparison

find_opportunities

High impressions but low CTR, queries ranking #8-20, pages losing clicks

inspect_url

Is this page indexed, last crawl, Google's canonical

sitemaps

Sitemap status, errors and URL counts

page_check

Title, description, canonical, noindex, headings, thin content, alt text, structured data errors

algorithm_updates

Google's own ranking update history, so you know whether a drop was an update

Totals come from the date dimension, so they match the Search Console UI. (Summing page rows double-counts impressions.)

Related MCP server: SearchConsole.ai

Setup (about 10 minutes)

You need a Google credentials file that can read Search Console. A service account is the most reliable option.

  1. In Google Cloud Console, pick or create a project and enable the Google Search Console API.

  2. Go to IAM & Admin > Service accounts, create one (no roles needed), then Keys > Add key > JSON. Save the file somewhere safe.

  3. In Search Console, open Settings > Users and permissions > Add user, paste the service account email, and choose Restricted. Repeat for each site.

  4. Add the server to your client (below), pointing GOOGLE_APPLICATION_CREDENTIALS to the JSON file.

Already use gcloud? This also works instead of steps 1-3:

gcloud auth application-default login --scopes=https://www.googleapis.com/auth/webmasters.readonly,https://www.googleapis.com/auth/cloud-platform

Claude Desktop

In claude_desktop_config.json:

{
  "mcpServers": {
    "searchlink": {
      "command": "npx",
      "args": ["-y", "searchlink-lite"],
      "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/key.json" }
    }
  }
}

Claude Code

claude mcp add searchlink -e GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json -- npx -y searchlink-lite

Cursor

In ~/.cursor/mcp.json, use the same block as Claude Desktop.

As a plugin

This repo ships a plugin manifest (.claude-plugin/plugin.json) and an MCP config (.mcp.json), so clients that install plugins from a repository can pick the server up without a config file of their own. Credentials still come from GOOGLE_APPLICATION_CREDENTIALS or your gcloud application default credentials.

One file install

If your client supports MCP bundles, download searchlink-lite-0.2.0.mcpb from Releases and open it. It asks for your credentials file and nothing else.

It is also in the official MCP Registry as com.namubase.searchlink/searchlink-lite.

Requires Node.js 18 or newer.

Privacy

Everything runs locally. Your credentials and data go only to Google's APIs. Nothing is sent to us.

Want it without the setup?

SearchLink is the hosted version (see a live report, no sign-in): sign in with Google (no key files), and it adds change tracking with before-and-after measurement, content decay, brand split, history kept past Google 16 months, Copilot citation tracking, page speed, a one-screen dashboard, a Monday email with 3 things to fix, and daily alerts when clicks drop. Works in Claude, ChatGPT and Cursor. Free for up to 3 sites.

list_sites and site_overview end with one line about the hosted version. Set SEARCHLINK_LITE_QUIET=1 in the server's env to turn it off. It is a plain link; nothing is sent anywhere unless you click it.

License

MIT

Available Tools

8 tools
algorithm_updatesGoogle updatesA
Read-onlyIdempotent

Google's official ranking and spam update history from the Google Search Status Dashboard, with start and end dates. Use it when traffic changed suddenly, to see whether an update lines up, before blaming the site's own edits. Needs no credentials. Read-only.

Inputs: days.

find_opportunitiesFind opportunitiesA
Read-onlyIdempotent

Finds the quickest wins: queries seen often but rarely clicked (rewrite the title or description), queries ranking #8 to #20 (one push from page one), and pages losing clicks. Use when the user asks what to improve or where to start. Returns each item with its numbers and the suggested fix. Read-only.

Inputs: site (required), days, limit.

inspect_urlCheck if a page is indexedA
Read-onlyIdempotent

Asks Google's URL Inspection API about one page: whether it is indexed, the coverage state, last crawl time, the canonical Google chose versus the one you declared, and robots or fetch problems. Use for "is this page on Google?" questions. For on-page problems use page_check. Read-only; Google allows about 2,000 inspections a day per property.

Inputs: url (required), site (required).

list_sitesList my sitesA
Read-onlyIdempotent

Lists every Search Console property the credentials can read, with the access level of each. Call this first when the user has not named a site, or when another tool says a site was not found. Read-only. Returns a table of property URLs and permissions.

Inputs: no named parameters.

page_checkCheck one pageA
Read-onlyIdempotent

Fetches one public page the way a search engine does and checks the title, meta description, canonical, noindex and robots.txt, H1 headings, word count, image alt text and structured data. Returns what it found and a list of problems in order of importance. Works without any Google credentials. Read-only: it only downloads the page.

Inputs: url (required).

search_performanceSearch performance (custom)A
Read-onlyIdempotent

Custom Search Console report when site_overview is not specific enough: group by query, page, country, device or date (up to two at once), filter by query or page text, sort, and optionally add the change against the previous period. Returns a table with clicks, impressions, CTR and position per row. Read-only.

Inputs: site (required), days, limit, sort_by, +4 more.

sitemapsSitemap statusA
Read-onlyIdempotent

Lists the sitemaps submitted for the site in Search Console, with when Google last read each one, errors, warnings and how many URLs it contains. Use for indexing questions about many pages at once. Read-only; it does not submit or change sitemaps.

Inputs: site (required).

site_overviewSite overviewA
Read-onlyIdempotent

The first tool to call for any question about how a site is doing on Google. Returns total clicks, impressions, CTR and average position for the period against the period before (totals match the Search Console UI), the pages that gained and lost the most clicks, and up to 3 plain-language things to do now. For custom breakdowns use search_performance instead. Read-only.

Inputs: site (required), days.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct read-only Search Console or SEO concern, and the descriptions include explicit guidance on when to use one instead of another. Even similar pairs like inspect_url vs. page_check and site_overview vs. search_performance are clearly separated by purpose and use cases.

    Naming Consistency4/5

    All tool names use lowercase snake_case and are short and readable, but they do not follow a single strict verb_noun pattern: list_sites and inspect_url are verb-first, while site_overview and sitemaps are noun-first. This is a minor deviation rather than a chaotic mix.

    Tool Count5/5

    Eight tools is well within the ideal range for a focused read-only Search Console server. Each tool covers a distinct workflow without redundancy or scope creep, and none of them feel like filler.

    Completeness4/5

    The tool surface covers the main read-only SEO workflows: property discovery, performance reporting, opportunity identification, URL inspection, on-page checks, algorithm context, and sitemap health. A whole-site index coverage report is missing, but agents can approximate it using sitemaps and inspect_url, so the gap is not severe.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Read-only MCP server that gives AI clients access to Google Search Console data, enabling natural language queries about traffic, rankings, and SEO opportunities.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Read-only MCP server for Google Search Console data, enabling search analytics, URL inspection, indexing diagnostics, and sitemap management through MCP clients.
      13 npm
      1
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables Google Search Console data queries via MCP, including search analytics, performance comparisons, URL inspection, and sitemap management.
      12
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides read-only access to Google Search Console data, including search analytics, sitemap status, and URL inspection, for MCP clients like Claude.
      5 npm
      MIT