mcp-gsc
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 3 tools tried
Contacts while installing and starting: api.github.com
What it contacted
api.github.com
Hosts it looked up or connected to while installing and starting with no input, watched from outside its sandbox. The npm registry is left out. Says nothing about what its tools contact when called.
Starting it
npx -y mcp-gsc@0.4.1
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
3 tools that take no input and look read-only were called once with nothing. 0 returned a result.
list_properties | No usable answer tool reported an error: Invalid environment configuration: - GOOGLE_GSC_CREDENTIALS_PATH: Invalid input: expected string, received undefined |
list_sitemaps | No usable answer tool reported an error: Invalid environment configuration: - GOOGLE_GSC_CREDENTIALS_PATH: Invalid input: expected string, received undefined |
sitemap_health | No usable answer tool reported an error: Invalid environment configuration: - GOOGLE_GSC_CREDENTIALS_PATH: Invalid input: expected string, received undefined |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
list_properties
List all Google Search Console properties you have access to, with permission levels and verification status.
get_property_details site_url
Get verification info, ownership, and permissions for a specific Google Search Console property.
search_analytics site_url, start_date, end_date, dimensions, type, data_state, dimension_filters, row_limit, start_row, brand_filter
Query Google Search Console search performance data (clicks, impressions, CTR, position) with filtering and grouping. DIMENSIONS: query, page, country, device, date, searchAppearance, hour - "hour" requires data_state="hourly_all" and is limited to the last 10 days - "searchAppearance" CANNOT be combined with "query" or "page" (API restriction) TYPE: web (default), image, video, news, discover, googleNews - "discover" = Google Discover feed. "googleNews" = Google News tab (distinct from "news") DATA STATE: Controls data freshness. - "all" (default) includes recent incomplete data matching the GSC dashboard - "final" returns only confirmed data with a 2-3 day lag, useful for stable reporting - "hourly_all" enables hourly granularity but data may be incomplete for the current day BRAND FILTER: Set to "brand_only" or "non_brand_only" to auto-filter queries by your domain name. Country codes use ISO 3166-1 alpha-3 format (e.g., 'usa', 'gbr', 'deu') — NOT alpha-2.
list_sitemaps site_url, sitemap_index
List all sitemaps for a property with status, type, indexed URL counts, errors/warnings.
get_sitemap site_url, sitemap_url
Get detailed info for a specific sitemap including content breakdown by type (web, image, video, etc.).
16 more tools
inspect_url site_url, url
Inspect a URL's indexing status, crawl info, rich results, mobile usability, and canonical URLs. Counts against the daily 2,000 and per-minute 600 URL Inspection limits.
batch_inspect_urls site_url, urls
Inspect up to 10 URLs simultaneously. Returns categorized results (indexed, not indexed, issues). Each URL counts against the daily 2,000 and per-minute 600 URL Inspection limits.
export_csv site_url, start_date, end_date, dimensions, type, dimension_filters, output_path
Export search analytics data to a CSV file on the machine running this server. Pages through results internally (25K rows per API call, up to 40 calls) to write the full dataset, bypassing the tool response row cap. Note: Google itself caps how many rows it exposes per day and search type (sorted by clicks), so very large sites may not get the complete long tail. Use dimension_filters to split the export into smaller slices if needed.
performance_overview site_url, start_date, end_date, type
Aggregate metrics (total clicks, impressions, avg CTR, avg position) plus a daily trend breakdown for a property. Single API call.
compare_periods site_url, start_date_1, end_date_1, start_date_2, end_date_2, dimensions
Compare two date ranges with delta calculations (absolute change + percentage change) for each dimension value. Makes 2 API calls.
top_movers site_url, start_date, end_date, comparison_days, metric, limit
Biggest gains and drops in clicks/impressions/position between two periods. Period A = start_date to end_date. Period B = the comparison_days before start_date.
device_country_breakdown site_url, start_date, end_date, breakdown
Performance breakdown by device type and/or country.
quick_wins site_url, start_date, end_date, min_impressions, max_ctr, min_position, max_position
Find high-impression, low-CTR queries in striking distance (position 4-20). These are opportunities to improve rankings and CTR with small content or SEO tweaks.
cannibalization site_url, start_date, end_date, mode, min_impressions
Detect keyword cannibalization — multiple pages ranking for the same query. Uses query + page dimensions to find overlap.
opportunity_finder site_url, start_date, end_date, comparison_days
Find queries with improving impressions but low clicks, new emerging queries, and declining performers. Makes 2 API calls to compare periods.
position_tracking site_url, start_date, end_date, queries, pages, granularity
Track position changes for specific queries or pages over time. Uses date dimension with query/page filters. Returns daily or weekly averages.
ctr_anomalies site_url, start_date, end_date, min_impressions
Detect queries/pages with abnormally low or high CTR relative to their position. Uses expected CTR curves per position bucket and flags deviations.
content_decay site_url, start_date, end_date, decay_threshold, dimension, min_impressions
Detect pages/queries where impressions have dropped significantly compared to their historical peak within the 16-month API window.
weekly_seo_report site_url, start_date, end_date, comparison_days
All-in-one SEO report: runs performance overview + quick wins + top movers + indexing issues summary. Returns a combined markdown report.
indexing_coverage site_url, urls
Batch-inspect user-provided URLs and categorize by indexing status: indexed, not indexed, canonical mismatch, robots blocked, fetch error, other. Respects URL Inspection rate limits.
sitemap_health site_url
Analyze all sitemaps: error/warning patterns, submission freshness (days since last submitted), indexed vs submitted ratio per sitemap.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=22 |
| Source | github.com/pijusz/mcp-gsc |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-uSyWTLahFANuR1Aw4EBg7GT/0rPKilL536XzD0+feTgS3WXc2l21WMehUOIoGCB+di7x1dnFZ8jELug/PWwtdg== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/mcp-gsc)
New version out? Ask for a fresh report.