mcp-gscSAFE
Google Search Console MCP server for Claude, Cursor, ChatGPT, and any MCP client. Query clicks, impressions, average position, URL inspection, sitemaps, and eligible indexing workflows. Run locally with npm or self-host on Cloudflare Workers. Google OAuth, no API keys. By digestseo.com.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](https://modelcontextprotocol.io) [](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.AKzar1el/mcp-gsc) [](https://github.com/AKzar1el/mcp-gsc/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@digestseo/mcp-gsc) [](https://glama.ai/mcp/servers/AKzar1el/mcp-gsc)
Part of the [DigestSEO](https://digestseo.com/) suite of open-source SEO tools.
- Product: digestseo.com/gsc-mcp
- Engineering case study: DigestSEO MCP Suite — AI visibility, Search Console, web validation, and trend intelligence
- Support: digestseo.com/support
- Privacy: digestseo.com/privacy
The self-hosting launcher is available as `@digestseo/mcp-gsc`:
npx -y @digestseo/mcp-gsc
The npm launcher starts a loopback-only Streamable HTTP Worker on 127.0.0.1 (port 8080 by default); it is not a stdio MCP process. You can run the npx command from any directory because the launcher resolves its bundled Worker configuration from the installed package. Clients that launch the package should connect to http://127.0.0.1:8080/mcp after supplying the Google OAuth and token-encryption environment variables described in SETUP.md. The launcher exits before starting Wrangler if `GOOGLE_CLIENT
f075fd97fb51OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-gsc --env GOOGLE_CLIENT_SECRET=${GOOGLE_CLIENT_SECRET} --env TOKEN_ENCRYPTION_KEY=${TOKEN_ENCRYPTION_KEY} -- npx -y @digestseo/[email protected]Exposed tools (23)
18 read · 2 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
analytics.compare | read | |
analytics.query | read | |
indexing.list_pages | read | |
indexing.remove | destructive | |
indexing.request | read | |
indexing.status | read | |
insights.cannibalization | read | |
insights.content_decay | read | |
insights.page_queries | read | |
insights.query_pages | read | |
insights.quick_wins | read | |
reports.weekly_digest | read | |
server.capabilities | read | |
sitemaps.delete | destructive | |
sitemaps.get | read | |
sitemaps.list | read | |
sitemaps.submit | write | |
sites.add | write | |
sites.delete | destructive | |
sites.get | read | |
sites.list | read | |
urls.inspect | read | |
urls.inspect_many | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (16)
indexing.remove, sitemaps.delete, sites.delete
.dev.vars.example
import worker from '../../src/entrypoint';
import { type Env } from '../../src/index';import worker from '../../src/entrypoint';
import { GOOGLE_TOKEN_URL, GOOGLE_USERINFO_URL } from '../../src/google';import { type Env } from '../../src/index';The npm launcher starts a loopback-only **Streamable HTTP** Worker on `127.0.0.1` (port `8080` by default); it is not a stdio MCP process. You can run the `npx` command from any directory because the
http://127.0.0.1:8080/mcp
claude mcp add --transport http gsc http://127.0.0.1:8080/mcp
codex mcp add gsc --url http://127.0.0.1:8080/mcp
**ChatGPT** — ChatGPT cannot connect directly to this loopback `127.0.0.1` endpoint. For private/local use, create an OpenAI **Secure MCP Tunnel**, then run `tunnel-client` on the same machine as the
const binary = atob(b64);
@cloudflare/workers-oauth-provider, agents, wrangler, zod, @cloudflare/vitest-plugin, @cloudflare/workers-types, tsx, typescript
This repository is the **self-hostable core**: Google OAuth, encrypted refresh-token storage, and an MCP tool suite with read and write Google Search Console operations, plus an on-demand weekly diges
| **`server.capabilities`** | Read | List every tool this server exposes and report local Google credential state. `connected` means a stored refresh credential is present; the response also exposes `
Gates applied: no_behavioural_pass.
f075fd97fb51full audit observations/trust-audit/mcp-server/akzar1el__mcp-gsc.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f075fd97fb51 | SAFE | B | 89 | first audit |
Questions
What is the mcp-gsc MCP server?
Google Search Console MCP server for Claude, Cursor, ChatGPT, and any MCP client. Query clicks, impressions, average position, URL inspection, sitemaps, and eligible indexing workflows. Run locally with npm or self-host on Cloudflare Workers. Google OAuth, no API keys. By digestseo.com.
What tools does mcp-gsc expose?
23 in total: 18 read-only, 2 that write, and 3 that can delete or overwrite (indexing.remove, sitemaps.delete, sites.delete). Every one is listed on this page with its risk.
Is mcp-gsc safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does mcp-gsc need?
It reads GOOGLE_CLIENT_SECRET, MCP_ACCESS_TOKEN and TOKEN_ENCRYPTION_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mcp-gsc run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @digestseo/mcp-gsc at 0.4.36.
How current is this page?
The grade is for one exact copy of the source (f075fd97fb51), read on 2026-10-11. The repository is watched and re-audited when it changes.