GSC Opportunity MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CREATOR_SEO_SITE | Yes | The Google Search Console property to query, preferably in domain property form such as sc-domain:example.com. | |
| RAPTIVE_CLIENT_ID | No | Optional Raptive client ID; used with RAPTIVE_CLIENT_SECRET to enable real per-page RPM. | |
| CREATOR_SEO_SITE_RPM | No | Display-ad revenue per 1000 pageviews used for revenue estimates. Default is 5. | |
| RAPTIVE_CLIENT_SECRET | No | Optional Raptive client secret; used with RAPTIVE_CLIENT_ID to enable real per-page RPM. | |
| GOOGLE_APPLICATION_CREDENTIALS | No | Absolute path to a Google service account JSON key. Optional alternative to user Application Default Credentials. | |
| CREATOR_SEO_AFFILIATE_CATEGORIES | No | A JSON map of query/page substring to extra dollars per 1000 clicks, e.g. {"smart ring": 40}. Default is {}. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| health_checkB | Auth + config status. Never hangs on expired tokens (headless-safe). |
| list_sitesA | List Search Console properties the credentials can read. |
| get_striking_distance_keywordsB | Queries ranking ~4-15 (page-2-to-top-3) — the most actionable growth band. Each row reports the ranking page and the gap to page 1 (position - 3). |
| get_page_performanceC | Full GSC picture for one URL: totals + the queries driving it. |
| analyze_content_decayC | Pages losing clicks month-over-month (current window vs prior window). |
| find_cannibalizationC | Queries where two+ pages compete — authority is being split. |
| get_top_opportunitiesA | The headline: combine striking-distance, decay, and cannibalization into one ranked action list. Revenue-weighted with REAL per-page Raptive RPM when Raptive creds are configured in .env, else the flat CREATOR_SEO_SITE_RPM. |
| get_raptive_revenueB | Real Raptive revenue for the window: total $, pageviews, and blended RPM. Requires RAPTIVE_CLIENT_ID/SECRET in .env; raises a clear error otherwise. |
| get_raptive_page_performanceB | Per-page Raptive RPM + earnings for the window (highest revenue first). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target a clearly distinct analytical question (decay, cannibalization, striking-distance, revenue). The main overlap is get_page_performance (GSC metrics for one URL) vs get_raptive_page_performance (Raptive RPM for pages), which are distinguishable only by the 'raptive' prefix, and get_top_opportunities partially aggregates the three analysis tools, so an agent may sometimes pick the detailed tool when the summary was wanted.
Strong snake_case convention with clear verb prefixes (get_/list_/analyze_/find_). health_check deviates from the verb_noun pattern, and find_cannibalization uses a concept rather than an object, but overall the pattern is predictable and readable.
Nine tools cover a narrow, well-defined SEO-analysis surface with each tool earning its place. No filler or near-duplicate tools beyond the intentional GSC-vs-Raptive split.
The surface covers the core lifecycle: auth check, property listing, per-page GSC detail, three distinct opportunity analyses, a combined ranking, and Raptive revenue (total and per-page). Minor gaps exist, such as no explicit date-range/window parameter tool and no query-level search outside the striking-distance band, but agents can work around these via the provided endpoints.