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.

DimensionOtaKit MCP ServerPush OTA updates to your Capacitor app without app store reviewsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS57 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Teams building Android/iOS apps with Capacitor that want to ship web asset updates without app store reviews
  • Developers using Claude Code, Codex, or VS Code who want agent-assisted OTA releases
  • Organizations that need to self-host their OTA update platform
  • 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
  • Non-Capacitor projects or apps that do not use OtaKit
  • Updates that require native code changes rather than web assets
  • Teams unwilling to grant an agent upload and release permissions
  • 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
  • Requires signing in to an OtaKit account (npx @otakit/cli login) for access to consoles, organizations, and projects
  • The CLI writes client configuration files (connect prints the exact file it will write)
  • Uploading bundles and creating releases requires write access to the relevant project
  • The remote endpoint https://console.otakit.app/mcp involves OAuth authorization
  • 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
  • Publishing without approval could push a broken build to real devices
  • Upload and release operations change the manifests served on a channel, affecting subsequent app launches or resumes
  • Self-hosting means maintaining Postgres, an S3-compatible bucket behind a CDN, and optionally the ingest service and a Tinybird workspace
  • The CLI writes config files, so the target path printed by connect should be verified first
  • 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, Codex, VS CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00