A practical MCP workflow
Find keyword opportunities with Google Search Console and MCP
Connect your own verified Google Search Console property to ToolCargo, compare matching reporting periods, and inspect query–page pairs with impressions. Use those observed searches to improve the page that already serves that intent before creating another landing page.
Built for: Site owners and SEO teams who need to decide what to improve using observed searches rather than assumed keyword demand.
What to connect
Create a ToolCargo account and use OAuth or an API key with a supported MCP client. Hosted connectors share your plan’s call quota; connect each required MCP endpoint separately. Review provider permissions before starting.
Run the workflow
1. Connect an authorized Google account
Sign in to ToolCargo and connect Google Search Console with read access. Your account must have access to the property. Google connections currently require invited test accounts; ask support if your account cannot authorize the app.
2. Build a comparable baseline
Use list_properties to choose the exact property. Request search_performance by query and page for 28 days and compare with the previous matching period. The connector ends periods three days ago; top returned rows do not represent every query.
3. Investigate queries with existing impressions
Use striking_distance to review query–page pairs at average positions 8–20. Inspect the search intent and the existing page before changing it. A position average can mix devices, countries and result types, so it is a starting point rather than a guaranteed quick win.
4. Choose a useful page change and measure again
Use page_insights to connect a page’s queries to your saved audit findings. Improve the answer, title or internal links where the evidence supports it. Create a new landing page only for a distinct useful intent. Record the release date and compare equivalent periods after fresh data arrives.
A prompt to try
For my verified property, compare the last 28 available days with the previous period. Show query–page pairs with impressions and average positions 8–20. For each candidate explain its intent, which existing page should serve it and one evidence-based improvement. Do not invent search volumes or forecast rankings.
What a useful result looks like
Example decision record: query → current landing page → impressions/clicks/CTR/average position → observed content gap → one proposed update → release date → later period comparison. Use the actual values returned by Google; an empty report is not proof that tracking is broken.
Know the limits
The connector is read-only. It does not submit sitemaps, request indexing or change Search Console settings. Google may omit some queries and returns top rows. CTR and position vary with intent and result layout, and changes do not establish causation on their own.
Common questions
Can MCP submit my sitemap to Google?
ToolCargo Search Console requests webmasters.readonly. Submit your sitemap in the native Google Search Console interface with an account that has the required permissions.
Should every keyword become a landing page?
No. Related queries can belong on the same useful page. Create a separate page when the task and answer differ enough to justify it, then link it from relevant existing content.
Does Search Console show all organic visitors?
No. It reports Google Search performance, with reporting limits. Use your site analytics for visits and conversions, and keep those metrics separate from Search Console clicks.
References and tool documentation
Use the provider’s documentation to check the underlying concepts, and ToolCargo’s references for the exact tools, inputs and limits.
- Google: Search Console performance metrics
Review clicks, impressions, CTR, average position and the dimensions used to group results.
- Google: sitemap submission and fetch troubleshooting
Follow the native Search Console steps for submission and live fetch checks; the ToolCargo connector stays read-only.
Tool references for this workflow
Continue with the tools
Related workflows
- Find image candidates and inspect their credits with AI and MCP
- How to run an SEO audit with an AI agent and MCP
- Compare npm and PyPI packages with an AI agent
- Monitor SEO changes after launch with an AI agent and MCP
- Find research papers and verify DOI metadata with an AI agent
- Check npm and PyPI package vulnerabilities with an AI agent
- Find life-sciences publications with Europe PMC and MCP
- Find research datasets with an AI agent and DataCite MCP
- Review Rust crate versions and dependencies with MCP
- Research species and biodiversity records with MCP
- Compare public AI model and dataset metadata with MCP
- Find books and compare editions with MCP
- Resolve entities and review Wikidata statements with MCP
- Review US weather forecasts with an AI agent and MCP
- Compare country indicators with AI and World Bank MCP