gsc-mcp
Enables programmatic management of Google Search Console properties and IndexNow URL submission for search indexing.
README
gsc-mcp
MCP server for Google Search Console and IndexNow — manage search indexing programmatically instead of driving a browser.
- Image:
ghcr.io/robertdwhite/gsc-mcp, built by CI in this repo. - Transport: MCP streamable HTTP at
/mcp, bearer-gated byMCP_TOKEN./healthzis open.
Tools
| Tool | Does |
|---|---|
gsc_status() |
Credential check; reports the service-account email |
list_sites() / add_site(site_url) |
Search Console properties |
verification_token(site_url, method) |
Get FILE/META ownership token |
verify_site(site_url, method) |
Complete verification — the service account becomes an owner |
add_owner(site_url, email) |
Grant a human Google account access (UI + API) |
submit_sitemap(site_url, sitemap_url) / list_sitemaps(site_url) |
Sitemap management with indexed-count stats |
search_analytics(site_url, days, dimensions, row_limit) |
Clicks/impressions/CTR/position by query, page, country, device, date |
inspect_url(site_url, url) |
Per-URL index status, last crawl, canonical |
submit_indexnow(urls, host, key) |
Push URLs to Bing/DuckDuckGo/Yandex — works with no Google setup |
One-time Google setup (human, ~5 minutes)
- In Google Cloud Console, create/reuse a project and enable Google Search Console API and Site Verification API.
- Create a service account (no roles needed) and a JSON key.
- Put the key JSON in the
GSC_SA_JSONenv var (in-cluster: thegsc-mcp-envsecret).
Then, via tools: add_site → verification_token (place the token on the
site) → verify_site → the service account is a verified owner and every
other tool works. add_owner grants your personal account the same property.
Config (env)
| Var | Meaning |
|---|---|
MCP_TOKEN |
Bearer token required on /mcp. Unset = unauthenticated (dev only). |
GSC_SA_JSON |
Service-account key JSON (the raw JSON string). |
INDEXNOW_HOST / INDEXNOW_KEY |
Optional defaults for submit_indexnow. |
PORT |
Listen port (default 8080). |
Deploy
Manifests live in
whitehouse-rke2 under
apps/ai/gsc-mcp (endpoint https://gsc-mcp.internal.white.fm/mcp, tailnet
only).
Connecting clients
The server speaks MCP streamable HTTP at /mcp and expects
Authorization: Bearer <MCP_TOKEN>. Anything below works from any machine
that can reach the endpoint (for the house deploy: tailnet/LAN only).
Claude Code
claude mcp add --transport http gsc https://gsc-mcp.internal.white.fm/mcp \
--header "Authorization: Bearer <MCP_TOKEN>"
Or directly in ~/.claude.json:
"mcpServers": {
"gsc": {
"type": "http",
"url": "https://gsc-mcp.internal.white.fm/mcp",
"headers": { "Authorization": "Bearer <MCP_TOKEN>" }
}
}
Claude Desktop
The custom-connector UI expects OAuth; this server uses a static bearer, so
bridge it with mcp-remote in
claude_desktop_config.json (needs Node):
"mcpServers": {
"gsc": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://gsc-mcp.internal.white.fm/mcp",
"--transport", "http-only",
"--header", "Authorization: Bearer <MCP_TOKEN>"]
}
}
Codex (ChatGPT app / Codex CLI)
Codex configures MCP servers as stdio commands — use the same bridge in
~/.codex/config.toml:
[mcp_servers.gsc]
command = "npx"
args = ["-y", "mcp-remote", "https://gsc-mcp.internal.white.fm/mcp",
"--transport", "http-only",
"--header", "Authorization: Bearer <MCP_TOKEN>"]
startup_timeout_sec = 60
Restart the app after editing.
Hermes (or any YAML-config MCP client)
mcp_servers:
gsc:
url: https://gsc-mcp.internal.white.fm/mcp
headers:
Authorization: Bearer ${GSC_MCP_TOKEN}
Sanity check without a client
curl -s https://gsc-mcp.internal.white.fm/healthz # -> ok (no auth)
curl -s -o /dev/null -w '%{http_code}\n' -X POST \
https://gsc-mcp.internal.white.fm/mcp # -> 401 (auth gate works)
Note: claude.ai web connectors cannot reach a tailnet-only endpoint; expose
an external route first if you need it there.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。