io.github.antohins/seo-tools-mcp-gsc

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  warn25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  tool "gsc_query" param "page" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "gsc_inspect_url" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "gsc_get_sitemap" param "feedpath" description: off-vendor URL in a description (example.com); capability text should not name where data goes.

• Supply chain

  pass25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  repository linkage verified

• Credential hygiene

  fail15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  tool "gsc_set_credentials" has a secret-shaped input parameter "GOOGLE_CLIENT_SECRET" — secrets must never be tool parameters (the model would supply/handle the credential). tool "gsc_set_credentials" has a secret-shaped input parameter "GSC_REFRESH_TOKEN" — secrets must never be tool parameters (the model would supply/handle the credential). tool "gsc_oauth_start" has a secret-shaped input parameter "clientSecret" — secrets must never be tool parameters (the model would supply/handle the credential).

• Permission scope

  pass15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• Version behavior

  warn10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 1.7.0 (minor bump): new tool "gsc_auth_status" appeared; new tool "gsc_set_credentials" appeared; new tool "gsc_oauth_start" touches a sensitive surface (email/exec/net/fs); new tool "gsc_oauth_finish" appeared; new tool "gsc_save_sa_json" appeared; new tool "gsc_query" touches a sensitive surface (email/exec/net/fs); new tool "gsc_list_sites" appeared; new tool "gsc_get_site" appeared; new tool "gsc_inspect_url" touches a sensitive surface (email/exec/net/fs); new tool "gsc_list_sitemaps" appeared; new tool "gsc_get_sitemap" appeared.

• Transport config

  unscannable10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.