M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionGoogle Search Console MCP ServerAnalyze Google Search Console SEO data through natural-language chats with your AI assistantBioMCPOne binary. One grammar. Evidence from the biomedical sources you already trust.
FMRS63 / 100 · C75 / 100 · B
Reliability10 / 2010 / 20
Security and permissions10 / 2016 / 20
Maintenance13 / 2018 / 20
Documentation16 / 2017 / 20
Setup experience14 / 2014 / 20
Best for
  • SEO practitioners who regularly analyze GSC search performance data
  • Users of MCP-compatible clients such as Claude Desktop, Cursor, Codex CLI, Gemini CLI, or Antigravity
  • Individuals and small teams who prefer natural-language conversation over manually exporting reports
  • Users willing to configure their own Google Cloud credentials and run the server locally
  • Biomedical researchers
  • Clinicians
  • AI agents that need efficient access to biomedical literature and data analysis
Not for
  • Users who only want claude.ai in the browser and won't install the desktop app (the MCP server runs locally)
  • Users who don't want to create a Google Cloud project and API credentials
  • Users who need a hosted one-click sign-in with GA4 tools (the source points to a separate hosted version limited to 100 seats)
  • Users running a cloned install on Python 3.10 or older
  • Users needing to write to upstream databases (read-only)
  • Users requiring direct access to closed datasets (e.g., COSMIC is not directly integrated)
  • Users expecting all advanced features without API keys
Required permissions
  • Google Search Console API access (read search analytics and site data)
  • OAuth path requires Google account authorization, with the token cached locally
  • Service account path requires adding the service account email as a Full access user on your GSC property
  • Credential JSON file paths are provided by the user via the client config env
  • Destructive operations (add_site, delete_site, delete_sitemap) are disabled by default and require explicitly setting GSC_ALLOW_DESTRUCTIVE=true
  • Requires internet access to query public biomedical APIs
  • Optional API keys (NCBI, Semantic Scholar, OpenFDA, etc.) to improve rate limits or unlock features
  • Local read/write access for skills, cache, and local study data (e.g., `~/.local/share/biomcp`)
Risks and side effects
  • Credential JSON files contain sensitive keys and must be protected and kept out of version control
  • If GSC_ALLOW_DESTRUCTIVE is enabled, the AI assistant can perform destructive actions such as adding/removing sites and deleting sitemaps
  • Remote deployment with sse transport bound to 0.0.0.0 exposes the service on the network, so you must assess access-control risk yourself
  • OAuth tokens are cached in the local platform user config directory, which may have access boundaries on multi-user machines
  • Service account keys are long-lived, so a leak has a broad impact
  • Upstream API rate limits may affect performance
  • Some data sources (e.g., KEGG) have licensing terms that restrict non-academic use
  • Features requiring API keys (e.g., OncoKB) may be incomplete without them
  • Local binary installations need regular updates for compatibility
Supported clientsClaude Desktop, Cursor, Codex, Gemini CLI, AntigravityClaude Desktop, Claude Code, Codex, Other MCP stdio clients
Tools1511