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.

DimensionVarlock Docs MCP ServerOfficial documentation MCP server for Varlock, available over HTTP/SSEMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS38 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation7 / 2018 / 20
Setup experience6 / 2015 / 20
Best for
  • Developers already using Varlock to manage .env files who want their AI assistant to reference official documentation
  • Teams needing details on @env-spec syntax, CLI commands, or plugin configuration
  • 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 want to read or modify local .env file contents directly via MCP (not covered by this server — use the varlock CLI itself)
  • Scenarios requiring access to secret values or runtime environment variables (this server is documentation-only and does not handle secret data)
  • 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
  • As a remote, read-only documentation service, clients typically only need outbound HTTPS network access to reach the endpoint
  • No local filesystem or environment variable access is required (none is mentioned in the README)
  • 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
  • This is a remote service hosted at docs.mcp.varlock.dev, so its availability and data freshness depend on dmno-dev's operation rather than being locally controlled
  • The README does not state whether authentication or rate limiting is in place; review terms and privacy practices before connecting
  • If documentation lags behind code changes, the AI assistant could give outdated guidance
  • 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