Google Search ConsoleSAFE
Google Search Console Insights with Claude AI for SEOs
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that connects Google Search Console (GSC) to AI assistants, allowing you to analyze your SEO data through natural language conversations. Works with Claude Desktop, Cursor, Codex CLI, Gemini CLI, Antigravity, and any other MCP-compatible client.
Skip setup, get more. A more advanced hosted version — one-click sign-in, added GA4 tools. Works with Claude Desktop, Claude Code, Claude.ai, Codex, Cursor, and any MCP client. Only 100 seats. → **Advanced GSC MCP (hosted)**
What's New
[0.4.1] — September 2026
- `check_indexing_issues` runs concurrently — same fix as #31, so it no longer times out on 10-URL batches against
sc-domain:*properties. Thanks @kuldiph. (#55) - Removed a leftover dead `orderBy` in
get_search_by_page_query(the Search Analytics API ignores it). Thanks @kuldiph. (#55)
[0.4.0] — September 2026
- Rich-result issues now surface —
inspect_url_enhancedandbatch_url_inspectionread rich-result issues from the correct API path, so markup problems are reported instead of silently dropped. Thanks @patrickweh. (#46, #48) - `batch_url_inspection` runs concurrently — 10-URL batches no longer time out on
sc-domain:*properties. Thanks @remotesensei. (#31) - `compare_search_periods` deltas fixed — Period 1 is now the analyzed period and Period 2 the baseline, so growth reads as growth (not decline). Thanks @JKdreaming. (#42)
- `get_advanced_search_analytics` sorting works —
sort_by/sort_directionare now applied instead of silently ignored. Thanks [@kuldiph](https://githu
ca6a7b5c610bOBSERVED · 2026-09-24Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-search-console --env GSC_CREDENTIALS_PATH=${GSC_CREDENTIALS_PATH} --env GSC_OAUTH_CLIENT_SECRETS_FILE=${GSC_OAUTH_CLIENT_SECRETS_FILE} --env GSC_SKIP_OAUTH=${GSC_SKIP_OAUTH} -- uvx mcp-search-console{
"mcpServers": {
"mcp-search-console": {
"command": "uvx",
"args": [
"mcp-search-console"
],
"env": {
"GSC_CREDENTIALS_PATH": "${GSC_CREDENTIALS_PATH}",
"GSC_OAUTH_CLIENT_SECRETS_FILE": "${GSC_OAUTH_CLIENT_SECRETS_FILE}",
"GSC_SKIP_OAUTH": "${GSC_SKIP_OAUTH}"
}
}
}
}Exposed tools (21)
17 read · 2 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_site | write | |
batch_url_inspection | read | |
check_indexing_issues | read | |
compare_search_periods | read | |
delete_site | destructive | |
delete_sitemap | destructive | |
get_advanced_search_analytics | read | |
get_capabilities | read | |
get_creator_info | read | |
get_performance_overview | read | |
get_search_analytics | read | |
get_search_by_page_query | read | |
get_site_details | read | |
get_sitemap_details | read | |
get_sitemaps | read | |
inspect_url_enhanced | read | |
list_properties | read | |
list_sitemaps_enhanced | read | |
manage_sitemaps | read | |
reauthenticate | read | |
submit_sitemap | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
delete_site, delete_sitemap
google-api-python-client, google-auth-httplib2, google-auth-oauthlib, mcp, platformdirs
6. Add the service account email to your GSC property: Search Console → Settings → Users and permissions → Add user → Full access
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
ca6a7b5c610bfull audit observations/trust-audit/mcp-server/aminforou__google-search-console-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-24 | ca6a7b5c610b | SAFE | B | 89 | first audit |
Questions
What is the Google Search Console MCP server?
Google Search Console Insights with Claude AI for SEOs
What tools does Google Search Console expose?
21 in total: 17 read-only, 2 that write, and 2 that can delete or overwrite (delete_site, delete_sitemap). Every one is listed on this page with its risk.
Is Google Search Console safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Google Search Console need?
It reads GSC_CREDENTIALS_PATH, GSC_OAUTH_CLIENT_SECRETS_FILE and GSC_SKIP_OAUTH from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Google Search Console run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-search-console.
How current is this page?
The grade is for one exact copy of the source (ca6a7b5c610b), read on 2026-09-24. The repository is watched and re-audited when it changes.