AskWatch Google Search Console MCP

## What is AskWatch GSC MCP A hosted MCP server that gives Claude, ChatGPT, Cursor, Claude Code and any other MCP client read access to your Google Search Console data. You connect your Google account once and get a personal link. There is no Google Cloud project to create, no OAuth client to configure, no `credentials.json` on disk and nothing running on your machine. It is free, and the grant is read-only: it asks for `webmasters.readonly`, which cannot submit a sitemap, request indexing, remove a URL or change a property. ## Setup 1. Connect your Google account at [askwatch.ai/free-tools/google-search-console-mcp](https://askwatch.ai/free-tools/google-search-console-mcp). 2. Copy your personal link. 3. Add it to your client. Claude Code: ```bash claude mcp add --transport http askwatch-gsc https://mcp.askwatch.ai/gsc/YOUR_KEY ``` Cursor, VS Code, Windsurf, Codex and Gemini CLI take the same address in their own config file. The exact shape for each of the nine supported clients is on the tool page. The key also works as a header, for clients that prefer one: ``` Authorization: Bearer YOUR_KEY ``` ## Tools Seven tools answer a whole question, one passes anything through, three describe the account. | Tool | What it answers | | --- | --- | | `site_overview` | Clicks, impressions, CTR and average position for a period, each against the period before it | | `top` | Top queries, pages, countries or devices, optionally narrowed to one country or device | | `changes` | What gained and what lost between two periods, with small rows filtered out | | `find_opportunities` | Queries ranking 5 to 20 with a click-through rate below what is normal at that position | | `find_cannibalization` | Queries where more than one of your pages is being shown | | `page_queries` | What searches a specific page is shown for | | `brand_split` | Branded against non-branded search, split on terms you supply | | `query` | Direct Search Analytics query, for anything the shaped tools do not cover | | `list_sites` | Search Console properties this connection can read | | `inspect_url` | Index status of one URL, including the canonical Google picked | | `list_sitemaps` | Sitemaps submitted for the property and their status | Every tool is annotated `readOnlyHint`, so a client can tell reads from writes without asking you to confirm each call. ## Why the tools are shaped A server can pass the Search Console API through and let the model write the query, or it can carry tools that each answer a whole question. We do the second. "What dropped" has a right method: compare two windows of equal length, drop rows with too few impressions to mean anything, sort by absolute loss rather than percentage so a query going from 2 clicks to 1 does not top the list. A model assembling that from raw rows picks a method each time, and the methods differ. The raw `query` tool is still there for the questions nobody anticipated. It is the fallback, not the interface. Answers come back in one envelope: the period used, the date the data runs through, the criteria applied, and notes. ## Finalized data, not fresh Search Console data settles over about two days, and the API can return either finalized rows or everything it has so far. We ask for finalized. This is not a detail. On a live site, including the incomplete day reported clicks down 11.7 percent when the actual fall was 1.1 percent. The reader here is a model that will pass the number on as a fact and build advice on top of it, so the default matters more than it would in a dashboard. ## Limits Limits are here to stop a looping agent from spending your Google quota, not to ration a free tool. - 20 calls a minute is the only refusal. - Daily thresholds add a notice and then a small delay. Nothing is cut off. - URL Inspection has its own smaller budget, because Google meters that endpoint an order of magnitude tighter than the rest. - Answers are cached from 30 minutes to 30 days depending on how old the data is, so the same question asked twice does not cost your quota twice. ## Access and privacy - The grant asks for `webmasters.readonly` and nothing else. - Google tokens are encrypted before they are stored. The link is stored as a hash, so a dump of the table is not a set of working addresses. - Regenerate the link and the old address stops answering immediately. Withdraw the grant in your Google account and the whole connection ends. - What we keep: the properties your account can read, the cached answers, and a count of calls per tool per day. - AskWatch's use of information received from Google APIs follows the Google API Services User Data Policy, including the Limited Use requirements. We do not sell this data and we do not train models on it. ## Who makes it [AskWatch](https://askwatch.ai) monitors brand visibility in AI search: whether ChatGPT, Perplexity, Gemini and Google AI Overviews name your brand when buyers ask, and which sources they cite. Search Console tells you what Google search did. It says nothing about what the answer engines say, which is the gap AskWatch measures. The Search Console MCP server is free and stays free.

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here C+, 71.4/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ

Compared with peers

Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.

Readiness

Higher than 95% of peers

This listing 88 · peer median 81

Latency

Faster than 28% of peers

This listing 529 ms · peer median 326 ms

How many agent tools actually work · All statistics

Listed in

Directories this entry was found in.

How to connect

https://server.smithery.ai/askwatch/gsc/mcp

curl -X POST https://server.smithery.ai/askwatch/gsc/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'