# Google Search Console > Query Search Console clicks, impressions, and queries from an AI agent. [Canonical HTML page](https://top-mcps.com/mcp/google-search-console) · [server.json](https://top-mcps.com/mcp/google-search-console.json) · [methodology](https://top-mcps.com/about/methodology) ## Install ### Claude Desktop — `claude_desktop_config.json` Paste under mcpServers. Fully quit and reopen Claude after editing. ```json { "mcpServers": { "google-search-console": { "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### Claude Code — `CLI or .mcp.json` Run from your repo. Commit .mcp.json to share with your team. ```shell # export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json claude mcp add google-search-console -- npx -y mcp-server-gsc ``` ### Cursor — `.cursor/mcp.json` Global path: ~/.cursor/mcp.json. Reload window after editing. ```json { "mcpServers": { "google-search-console": { "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### VS Code — `.vscode/mcp.json` VS Code uses the "servers" key (not "mcpServers"). ```jsonc { "servers": { "google-search-console": { "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### Windsurf — `~/.codeium/windsurf/mcp_config.json` Open via Cascade → hammer icon → Configure. ```json { "mcpServers": { "google-search-console": { "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### Cline — `cline_mcp_settings.json` Open via the Cline sidebar → MCP Servers → Edit. ```json { "mcpServers": { "google-search-console": { "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### Continue — `~/.continue/config.json` Continue uses modelContextProtocolServers with a transport block. ```json { "experimental": { "modelContextProtocolServers": [ { "transport": { "type": "stdio", "command": "npx", "args": [ "-y", "mcp-server-gsc" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } ] } } ``` ### Codex CLI — `~/.codex/config.toml` Codex uses TOML. Each server is a [mcp_servers.] subtable. ```shell # ~/.codex/config.toml [mcp_servers.google-search-console] command = "npx" args = [ "-y", "mcp-server-gsc", ] env = { GOOGLE_APPLICATION_CREDENTIALS = "${GOOGLE_APPLICATION_CREDENTIALS}" } ``` ### Zed — `~/.config/zed/settings.json` Zed calls them "context_servers". Settings live-reload on save. ```jsonc { "context_servers": { "google-search-console": { "command": { "path": "npx", "args": [ "-y", "mcp-server-gsc" ] }, "env": { "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}" } } } } ``` ### ChatGPT — `ChatGPT → Apps directory` Google Search Console doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build. ```none ``` ## At a glance - **Maintainer:** Community (ahonn) - **Transport:** stdio - **Auth model:** OAuth 2.1 - **Required secrets:** GOOGLE_APPLICATION_CREDENTIALS - **Supported clients:** Claude, Cursor, VS Code, Windsurf, Any MCP-compatible client, Verified GSC property - **License:** MIT - **Language:** TypeScript - **Latest version:** latest - **Last verified:** 2026-06-15 - **GitHub stars:** 224 (fetched 2026-06-17T07:09:46.844Z) - **Score:** 63/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology) - **Source:** https://github.com/ahonn/mcp-server-gsc ## Tools & permissions | Tool | Description | Args | Side effects | |------|-------------|------|--------------| | `search_analytics` | Return clicks, impressions, CTR, and position for a property, with dimension filters, regex, and quick-wins detection. | `siteUrl: string, startDate: string, endDate: string` | read | ## Security & scope - **Access scope:** read-only - **Sandbox:** Authenticates with a Google service-account key that has read access to a verified Search Console property. The single exposed tool is a Search Analytics read — it cannot submit sitemaps, request indexing, or change property settings. Scope the service account to read-only access on only the properties the agent needs. - **Gotchas:** - The service-account JSON sits in a client config file in plaintext — rotate it if the config is shared. - Add the service-account email to the GSC property with restricted (read) access, not full — full access is unnecessary for Search Analytics. - Search Analytics data lags ~2 days; treat the most recent days as provisional in any agent-generated report. ## Quick answer **What it does.** Connects to Google Search Console and exposes search_analytics — query-level clicks, impressions, CTR, and position data with filtering and regex support — so an agent can analyse organic search performance without opening the GSC UI. **Best for:** - Organic query performance analysis - CTR and position auditing - Page-two "quick win" discovery - Click and impression trend analysis - Query-to-page mapping **Not for:** - URL inspection / index coverage workflows - Non-Google search engines - Properties you cannot verify in GSC ## Description A community-maintained MCP that connects an AI agent to Google Search Console via the official Search Analytics API. Its search_analytics tool returns the same clicks, impressions, CTR, and average-position data you see in the Performance report, with dimension filtering, regex matching, and a "quick wins" detection that surfaces queries ranking on page two. Authentication is a Google service-account key with read access to the property. ## Why it matters The Search Console Performance report is where organic SEO is measured, but its UI is slow for cross-cutting questions. An MCP lets an agent answer "which queries lost the most clicks month over month" or "find page-two queries with high impressions" in one call. ## Key features - Official Search Analytics API - Dimension filtering and regex matching - Quick-wins (page-two) detection - Service-account auth - Read-only by design - MIT licensed ## FAQ ### Is it free? Yes. The MCP is MIT-licensed and the Search Console Search Analytics API is free within Google quota. You need a Google Cloud project and a service account with read access to your verified property — there is no per-call charge. ### How does auth work? A Google Cloud service-account key (JSON) passed via GOOGLE_APPLICATION_CREDENTIALS. The service account email must be added as a user with at least restricted (read) access to the Search Console property you want to query. ### What does the "quick wins" feature do? It surfaces queries ranking just below page one (roughly positions 11–20) with meaningful impressions — the queries where a small content improvement is most likely to move a page onto page one. It is a filter over the same Search Analytics data, not a separate data source. ### Does it do URL inspection or index coverage? No. This MCP focuses on the Search Analytics (Performance) data. For URL inspection or index-coverage status you would need a different GSC MCP or the URL Inspection API directly. ## Changelog - **2026-06-15** — Refreshed install snippets and fact sheet; verified for 2026. - **2025-03-01** — Initial directory listing.