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.

DimensionCKBKnow your code. Change it safely. Ship with confidence.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS43 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance6 / 2016 / 20
Documentation12 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers using AI assistants who want them to have precise code awareness
  • Teams with large codebases needing efficient navigation
  • Anyone doing refactoring who wants to understand impact
  • Code reviewers who need the full picture of changes
  • Tech leads tracking architectural health over time
  • 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
  • Dynamic dispatch or runtime behavior analysis (use a debugger)
  • Generated code that isn't indexed
  • Code generation, linting, or formatting
  • Cross-repo calls (use federation for this)
  • 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
  • Read access to codebase files and git history
  • Generate and maintain SCIP indexes (local files)
  • Execute the MCP server process via stdio
  • Optionally create API tokens for authentication when using the index server
  • Optional network access for HTTP API server
  • 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
  • SCIP indexes may become stale, leading to inaccurate references or impact analysis
  • Indexing large codebases can be time and disk intensive
  • Dynamic or reflective code may be misanalyzed
  • Requires installing SCIP indexers, and language support quality varies
  • Inputs are not sanitized, so verify outputs
  • 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, Claude Code, Cursor, Windsurf, VS Code, OpenCode, GrokClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools390