Google Search Console MCP vs Google Webtools MCP
A side-by-side look at the Google Search Console MCP and Google Webtools MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
G
Google Webtools MCPMarketingGoogle Search Console + GA4 for AI agents: properties, reports, indexing, verification, SEO.51GoodAuth: oauth 2.0Verdict: choose Google Search Console MCP for marketing work as a local process; choose Google Webtools MCP for marketing. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Google Search Console MCP when
- You need dedicated capabilities in the Marketing domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: OAuth 2.0.
- You have the keys it needs:
GSC_CLIENT_ID, GSC_CLIENT_SECRET, GSC_REFRESH_TOKEN. - You want tools like
gsc_sites, gsc_site_details, gsc_query.
GChoose Google Webtools MCP when
- You need dedicated capabilities in the Marketing domain.
- Its auth model fits you: OAuth 2.0.
- You have the keys it needs:
GOOGLE_APPLICATION_CREDENTIALS. - You want tools like
list_properties, get_property_details, add_property.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | G Google Webtools MCP | |
|---|---|---|
| Category | Marketing | Marketing |
| Quality signal | 63/100 · Good | 51/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | OAuth 2.0 | OAuth 2.0 |
| Pricing | Free | Not declared |
| Required env vars | GSC_CLIENT_IDGSC_CLIENT_SECRETGSC_REFRESH_TOKEN | GOOGLE_APPLICATION_CREDENTIALS |
| Verified owner | Community listing | Community listing |
| GitHub stars | 9 | 7 |
| Directory activity | 4 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 17 | 39 |
| Full listing | View Google Search Console MCP | View Google Webtools MCP |
Tools & capabilities
Google Search Console MCP tools 17
gsc_sitesList every property the authenticated account can read. Call this first when a property string fails: it returns the exact `site_url` values the other tools expect, and whether each one is a domain property (`sc-domain:example.com`) or a URL-prefix property.gsc_site_detailsPermission level and property type for one property.gsc_queryQuery the Search Analytics report: clicks, impressions, CTR, position. This is the general-purpose tool. With no dates it covers the last 28 days ending today (UTC), with data_state=all so today's partial data is included, matching what the Search Console UI shows. Example: site_url="sc-domain:example.com", dimensions="query,page", period="last_28_days", row_limit=100. Returns a `# meta ...` line then a TSV table, or JSON with `meta` and `rows`. The meta names the exact range, the row count, whether more rows exist and the `start_row` to pass next.gsc_performance_overviewSite totals for a period, compared with the preceding one by default. Start here: it answers "is the site up or down" in one call, with the percentage change on every metric. `position_delta` is negative when the average position improves.gsc_compare_periodsJoin two periods on one dimension and rank the rows by click delta. Answers "what changed" without the model diffing two tables by hand. Rows present in only one period are kept, with zeros on the missing side; the biggest movers in both directions are returned, worst first. The meta counts how many rows gained and how many lost clicks.gsc_quick_winsQueries close enough to the top that a push would pay off. Ranked by the clicks each query would gain at `target_position`, not by impressions: a big query already near its ceiling is not an opportunity. The meta reports the thresholds that were applied.gsc_ctr_gapsRows that rank well but are clicked far less than their position implies. The snippet, not the ranking, is the problem, which makes these the cheapest fixes available. `expected_ctr` is what a result at that position normally earns.gsc_cannibalizationQueries where several pages of the site compete for the same result. Reads one page of up to 25,000 query/page pairs; on a very large property the tail is cut off, and the meta says how many pairs were analysed. Each row lists the competing pages with their own clicks and positions.gsc_traffic_dropsPages that lost clicks against the baseline, each with a likely cause. `diagnosis` separates a ranking loss from falling demand, a collapsed CTR and a page that disappeared: the four need different fixes, and the raw numbers for both periods are in the row so the call can be checked.gsc_content_decayPages sliding down month after month. A period comparison hides this: a page that halves over six months never shows a sharp drop in any single month-on-month check. One query per month runs in parallel.gsc_alertsWhat changed sharply enough to be worth a message today. Compares the last `window_days` against the window before it across both queries and pages, and returns only movements past the alerting rules: lost positions, collapsed CTR, dropped or vanished pages.gsc_portfolioEvery accessible property at a glance, ranked worst first. One row per property with the current period, the previous one and a health flag: critical below -30% clicks, warning below -15%. Use it to decide which property to look at before running anything else.- +5 more on the listing page
Google Webtools MCP tools 39
list_propertiesStarting point — see every GSC property you can access and your permission level on each.get_property_detailsCheck the type and permission level of one specific property.add_propertyRegister a new site in Search Console (verification is a separate step).delete_propertyDrop a property from the authenticated account's Search Console site list. Historical data is not destroyed — the property can be added back.list_sitemapsSee which sitemaps are submitted and whether Google reports errors or warnings.get_sitemap_detailsDrill into one sitemap: URL counts by content type, last download time, error and warning counts.submit_sitemapSubmit a new sitemap after publishing or moving one.delete_sitemapWithdraw a sitemap that is stale, duplicated, or returning errors.get_search_analyticsThe raw query — full control over dimensions, filters, search type, row limit, data state, aggregation. Use when the shaped tools below don't fit.get_performance_summary"How are we doing?" — clicks, impressions, CTR, position with period-over-period comparison. Trend advice is withheld when the previous period returned no data at all.compare_periodsCompare two explicit date ranges side by side (before/after a release, seasonal comparison).get_top_queriesTop queries by clicks, each scored against the CTR benchmark for its position.- +27 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Google Search Console MCP
{
"mcpServers": {
"acamolese-google-search-console-mcp": {
"command": "uvx",
"args": [
"mcp-google-search-console"
],
"env": {
"GSC_CLIENT_ID": "YOUR_GSC_CLIENT_ID_HERE",
"GSC_CLIENT_SECRET": "YOUR_GSC_CLIENT_SECRET_HERE",
"GSC_REFRESH_TOKEN": "YOUR_GSC_REFRESH_TOKEN_HERE"
}
}
}
}
Google Webtools MCP
No confirmed install command for Google Webtools MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Google Search Console MCP is categorized under Marketing and uses a local stdio subprocess. Google Webtools MCP belongs to Marketing and uses an install path we have not confirmed yet. Pick Google Search Console MCP for marketing work and Google Webtools MCP for marketing.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Google Webtools MCP has no confirmed install command yet — follow its own setup instructions.
Google Search Console MCP is listed as free. Auth: oauth 2.0. Google Webtools MCP has no declared pricing — check the project's own site. Auth: oauth 2.0. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add acamolese-google-search-console-mcp and google-webtools-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Google Search Console MCP has a quality signal of 63/100 (Good) with 4 views, 0 installs and 9 GitHub stars. Google Webtools MCP has 51/100 (Good) with 1 views, 0 installs and 7 GitHub stars.