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.

DimensionGitHub MCP ServerManage repos, issues & PRs from chatMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS66 / 100 · C79 / 100 · B
Reliability14 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Development teams that want to handle issues, files, and pull requests from a coding assistant
  • Maintainers automating repetitive GitHub workflows
  • 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
  • Environments that cannot provide a GitHub token
  • Organizations requiring every repository write to be confirmed manually in GitHub's UI
  • 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
  • A GitHub Personal Access Token
  • Least-privilege Contents, Issues, or Pull requests access for the target repositories
  • 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
  • A leaked high-privilege token can modify repository code and issues
  • The model can create incorrect branches, issues, or pull requests; retain human confirmation for writes
  • 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, VS CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools60