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.

DimensionHome Assistant MCP ServerVibe-code your Home Assistant setup from your IDE: automations, dashboards, themes and configs.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS39 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation9 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers who want to manage Home Assistant from AI-powered IDEs like Cursor, VS Code, or Claude Code.
  • Users who want to build and iterate on automations or dashboards using AI while retaining manual control.
  • Those who need robust, predictable API access to Home Assistant rather than SSH or ad-hoc scripts.
  • 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
  • Users who do not want to install the HA Vibecode Agent add-on or do not want extra custom components inside Home Assistant.
  • Users who need direct REST API or WebSocket access to Home Assistant without the intermediary agent.
  • Beginners who are not comfortable installing Node.js locally or using MCP protocol.
  • 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 access to the local file system (to run Node.js and npx).
  • Requires network access to the Home Assistant agent's port (usually 8099).
  • Requires environment variables HA_AGENT_URL and HA_AGENT_KEY for authentication.
  • The agent itself uses Home Assistant's SUPERVISOR_TOKEN to access internal APIs.
  • 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
  • Storing the Agent Key in mcp.json may be leaked if committed to git.
  • AI-generated actions may modify or delete configurations, potentially causing data loss, though Git versioning mitigates this.
  • Relies on a custom agent running inside Home Assistant, which could introduce security vulnerabilities if exposed.
  • May inadvertently affect production environments if not configured carefully.
  • 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 Desktop, Cursor, VS CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools70