This is a community-maintained, MIT-licensed, unofficial MCP server that connects Google Search Console to MCP-capable AI clients. Its strengths are broad coverage of the SEO workflow — properties, search analytics, URL inspection, and sitemap management — plus uvx-based installation without cloning, two authentication options, and optional sse transport for remote deployment. The trade-off is that users must create their own Google Cloud credentials and manage credentials and account permissions themselves, and the cloned install requires Python 3.11+. It suits SEO users willing to set things up themselves, and is not aimed at those who only want a web interface or don't want to manage credentials.
Strongest · Documentation 16/20 Weakest · Reliability 10/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Python 3.11+ · Docker · Prebuilt binary
GSC_OAUTH_CLIENT_SECRETS_FILE
Absolute path to your OAuth client secrets JSON; obtained by creating an OAuth Desktop client in Google Cloud Console after enabling the Search Console API.
GSC_CREDENTIALS_PATH
Absolute path to your service account JSON key; created in Google Cloud Console under the service account's Keys tab.
GSC_SKIP_OAUTH
Set to "true" to force service account authentication and skip the OAuth browser login entirely.
GSC_DATA_STATE
Data state, defaults to "all" to match the GSC dashboard; "final" returns only confirmed data (2–3 day lag).
GSC_ALLOW_DESTRUCTIVE
Set to "true" to enable add/delete site and delete sitemap tools; disabled by default.
MCP_TRANSPORT
Transport mode, defaults to stdio; set to sse for remote/network deployments.
MCP_HOST
Host to bind for remote deployments, default 127.0.0.1 (example uses 0.0.0.0).
MCP_PORT
Port to bind for remote deployments, default 3001.
{
"mcpServers": {
"gscServer": {
"command": "/FULL/PATH/TO/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/client_secrets.json"
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"gscServer": {
"command": "/FULL/PATH/TO/uvx",
"args": [
"mcp-search-console"
],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/client_secrets.json"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add gscServer -e GSC_OAUTH_CLIENT_SECRETS_FILE=/full/path/to/client_secrets.json -- /FULL/PATH/TO/uvx mcp-search-console
Run it in a terminal; replace any <…> placeholders with your own values first.
After saving the client config and restarting the app, ask your AI assistant "List my GSC properties" — seeing your properties confirms the connection; otherwise ask it to "call get_capabilities" to check auth status.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
This is a Model Context Protocol (MCP) server that connects Google Search Console (GSC) to AI assistants so you can analyze SEO data through natural-language conversation. It covers property management, search analytics and reporting, URL inspection and indexing status, and sitemap management, and can have the assistant visualize data with charts. The server runs locally and supports two authentication paths: OAuth browser sign-in (recommended, uses your own Google account) or a service account (for automation or team use). Client configs require absolute paths to your credentials file; on first use OAuth opens a browser window, after which the token is cached. It can run without installation via uvx, or from a cloned repository (requires Python 3.11+). It also supports remote/network deployment with MCP_TRANSPORT=sse and running in Docker. Tools provided include property listing, site details, search analytics, performance overview, period comparison, per-page queries, advanced filtered analytics, URL inspection, batch URL inspection, indexing issue checks, sitemap viewing and management, reauthentication, and get_capabilities.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision d49eea9e5efb Data synced 2026-10-19 Read the FMRS scoring method