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.

DimensionClaspCommand-line tool for developing Google Apps Script projects locallyMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS63 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance15 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers who want to develop Google Apps Script locally with their own editor and Git workflow
  • Teams that need version control and collaboration for Apps Script projects
  • Users who want an AI coding agent (Claude Code, Gemini CLI) to manage Apps Script projects directly
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • General cloud storage or database integrations unrelated to Apps Script
  • Scenarios requiring vendor-backed official support SLAs (the README explicitly states it is not an officially supported Google product)
  • Projects relying on clasp 2.x's built-in TypeScript transpilation (removed in 3.x — use a bundler like Rollup instead)
  • Non-interactive service-account authentication (README marks this as experimental/not currently working)
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Google OAuth access to read/write the user's Apps Script projects (script.projects, script.deployments, script.webapp.deploy, etc.)
  • Google Drive read-only metadata and file access (drive.metadata.readonly, drive.file) to list and create bound scripts
  • Google Cloud Service Usage API access to list/enable/disable advanced services
  • Cloud Logging read access to fetch script execution logs
  • Local credential storage in `.clasprc.json` (containing OAuth tokens) in the home or working directory
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • `clasp push` always replaces the entire remote project content (the Apps Script API has no atomic or per-file operations), so mistakes can overwrite remote code
  • OAuth scopes are broad — covering scripts, Drive files, logging, and API management — so leaked credentials (especially custom ones saved via `--creds`) carry meaningful exposure
  • MCP mode is explicitly experimental; the README states it currently offers only a limited tool subset and behavior may change
  • Service-account / application-default-credentials support is explicitly marked experimental and 'NOT WORKING,' and should not be relied on for production automation
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude Code, Gemini CLIClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00