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.

DimensionTerraVisionAutomatically turn Terraform code into professional cloud architecture diagrams.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS56 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions14 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience10 / 2015 / 20
Best for
  • Developers and platform engineering teams using Terraform
  • Teams maintaining multi-cloud architecture documentation
  • Users who want local processing of infrastructure code
  • 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
  • Projects that do not use Terraform
  • Workloads requiring complete Azure or GCP resource coverage
  • Users seeking server-side cloud discovery or remote infrastructure management
  • 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
  • It needs to read local Terraform projects, variable files, and optionally plan JSON and graph DOT files
  • Normal operation requires local Terraform, Graphviz, and Git installations
  • AWS credentials are needed when using AWS Bedrock for AI annotations
  • 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
  • Azure and GCP currently have partial support limited to core services, so diagrams may be incomplete
  • When Bedrock or another REST API annotation backend is enabled, metadata and a summary graph are sent to the configured model service; the README states that .tf source files are not sent
  • Generated diagrams depend on the accuracy of the Terraform, plan, or graph inputs and do not replace infrastructure validation
  • 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