About MCP Search Console
MCP Search Console is a multi-account server for querying Google Search Console data across sites and clients without restarting. It combines account routing, OAuth or service-account authentication, and retry handling for search and indexing operations.
Key features
- 01Route requests across multiple accounts
- 02Query search performance and compare periods
- 03Inspect URLs and indexing issues
- 04List and manage sitemap submissions
- 05Retry transient API failures
Use cases
- 01Compare search performance across accounts
- 02Audit URLs for indexing issues
- 03Submit or remove sitemaps with safeguards
- 04Switch account context without restarting
MCP support
The server exposes Google Search Console account management, analytics, URL inspection, and sitemap tools to MCP clients. Sitemap submission and deletion are guarded by a destructive-action flag.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx mcp-search-console-multiGSC_ACCOUNTS_CONFIGPath to accounts.json config file with GSC credentials. Defaults to ~/.config/mcp-search-console/accounts.jsonGSC_ALLOW_DESTRUCTIVESet to 'true' to enable sitemap submit/delete operationsLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
17Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEmcp-search-console
Multi-account Google Search Console MCP server for operators who need one MCP surface across multiple sites or clients without restarting the server.
Release posture: beta package, version 0.1.3 from pyproject.toml.
Choose your path
| You are... | Start here | Then |
|---|---|---|
| Connecting the server to Claude/Codex/Cursor | docs/start-here.md | Quick start below |
| Auditing account routing or destructive guards | docs/architecture.md | gsc/server.py |
| Reviewing packaging or registry metadata | pyproject.toml | server.json |
Architecture
flowchart TD
U[AI operator] --> C[MCP client]
C --> S[FastMCP server]
S --> M[Account manager]
M --> F[Accounts config]
M --> A[OAuth or service-account auth]
S --> R[Retry wrapper]
R --> G[Google Search Console API]
G --> R --> S
Request flow
flowchart TD
P[Operator asks for analytics or indexing data] --> T[Selected MCP tool]
T --> A[Resolve named or default account]
A --> B[Build authenticated GSC client]
B --> C[Call Search Console endpoint]
C --> D{API call succeeds?}
D -- yes --> E[Return normalized JSON]
D -- retryable --> F[Backoff and retry]
F --> D
D -- no --> G[Return error payload]
Quick start
- Install the package.
python -m pip install mcp-search-console-multi
- Create the accounts config.
mkdir -p ~/.config/mcp-search-console
cp accounts.example.json ~/.config/mcp-search-console/accounts.json
- Register it in your MCP client.
{
"mcpServers": {
"search-console": {
"command": "uvx",
"args": ["mcp-search-console-multi"],
"env": {
"GSC_ACCOUNTS_CONFIG": "/Users/you/.config/mcp-search-console/accounts.json"
}
}
}
}
Available tools
| Tool group | Tools | Purpose |
|---|---|---|
| Account routing | list_accounts, set_default_account, reauthenticate | Inspect accounts, switch defaults, refresh auth |
| Property inventory | list_properties, get_site_details | Discover accessible properties and permissions |
| Search analytics | get_search_analytics, get_performance_overview, compare_periods, get_advanced_search_analytics, get_search_by_page | Query search-performance data |
| Inspection and sitemaps | inspect_url, batch_inspect_urls, check_indexing_issues, list_sitemaps, get_sitemap, submit_sitemap, delete_sitemap | Inspect indexing and manage sitemap submissions |
submit_sitemap and delete_sitemap stay behind the destructive flag documented in
docs/start-here.md.
Runtime proof
| Claim | Proof |
|---|---|
| Package entry point is stable | mcp-search-console-multi = "gsc.server:main" in pyproject.toml |
| Multi-account routing is first-class | AccountManager() and _get_manager() in gsc/server.py |
| Search Console calls are retried | with_retry() in gsc/server.py and gsc/retry.py |
| Auth is file-driven per account | accounts.example.json and gsc/accounts.py |
Repo map
| Path | Purpose |
|---|---|
gsc/server.py | FastMCP tool surface and response normalization |
gsc/accounts.py | Account config, auth loading, client construction |
gsc/auth/ | OAuth and service-account auth implementations |
gsc/retry.py | Retry behavior for transient API failures |
docs/start-here.md | Setup, env, validation, common failures |
docs/architecture.md | Component map and runtime lifecycle |
Validation
| Check | Command |
|---|---|
| Import compiles | python -m compileall gsc |
| Package builds | python -m build |
| README/docs links stay local | rg '\\]\\(([^)]+\\.md)\\)' README.md docs/ |
License
MIT
Project context for new tasks
Use INDEX.md to find task-specific contracts; consult prompt.md when product direction is relevant. Historical examples do not select the current task.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.