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.

DimensionBifrost MCP ServerBring VS Code's language intelligence to AIMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS51 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers using Cursor, Cline, Roo Code, or Windsurf.
  • Teams requiring AI-assisted code understanding and refactoring.
  • Environments leveraging VS Code language server capabilities.
  • 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 without AI integration or simple text editing needs.
  • Users preferring a terminal-only MCP server without VS Code.
  • 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
  • Listen on a local HTTP port for requests.
  • Read code file contents.
  • Execute code operations like symbol search and rename.
  • 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
  • Local server lacks authentication, potentially exposing sensitive code to malicious processes.
  • Port conflicts or occupation may cause service unavailability.
  • AI-initiated renames could break the codebase if not reviewed.
  • 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, Cline, Roo Code, WindsurfClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools190