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.

DimensionGitHubConnect AI assistants to GitHub through natural language.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS41 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation7 / 2018 / 20
Setup experience9 / 2015 / 20
Best for
  • Development teams that need AI assistants to operate GitHub
  • Users who want to handle repository collaboration tasks through natural language
  • Deployers able to manage GitHub access tokens securely
  • 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 do not need GitHub integration
  • Deployment environments that cannot provide a GitHub PAT or App token
  • Use cases requiring specific tools or permissions not documented in the source
  • 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
  • Requires a GitHub Personal Access Token or App token
  • stdio deployments must set GITHUB_PERSONAL_ACCESS_TOKEN
  • Remote connections require an authentication token in the Authorization header
  • The actual token permissions depend on the PAT or App token used
  • 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
  • Access tokens are secrets and should not be exposed
  • Repository, issue, pull request, and workflow operations may change GitHub data or project state
  • Overly broad token permissions may expand the actions available to the AI assistant
  • Misinterpreted natural-language requests may cause unintended GitHub operations
  • 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