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.

DimensionAutomotive 3DAutomotive 3D/AR visualization assistant built on SceneView SDK.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS36 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation5 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Developers building automotive 3D/AR apps with the SceneView SDK
  • Teams that want AI assistance to quickly prototype car configurators, HUDs, and dashboards
  • Automotive visualization projects on Android (Jetpack Compose), iOS (SwiftUI), or Web
  • 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-purpose 3D/AR work outside automotive (separate healthcare, gaming, and interior-design servers exist)
  • Directly controlling vehicle hardware or safety-critical systems
  • Use as a runtime rendering engine—this is a code-assistance MCP server, not a renderer
  • Strict production workflows that require a documented tool list and verified client compatibility (the provided material does not include those details)
  • 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
  • No permissions are documented for this server in the supplied material
  • It runs locally as a stdio process via npx, so Node.js and npm are required
  • First run requires network access to the npm registry to fetch the automotive-3d-mcp package
  • If the AI client writes generated code into a project, it will typically need file-system access per the client's configuration
  • 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
  • AI-generated automotive 3D/AR code may fail to compile or may not match SceneView APIs; human review and testing are required
  • Running an npm package via npx executes package code locally; verify the package name, version, and source
  • Automotive work can be safety-related, so generated output must never be used directly for vehicle control or safety-critical decisions
  • The setup depends on the npm supply chain and network environment; failures may come from network issues, Node versions, or client configuration
  • 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, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00