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.

DimensionGit MCP ServerA comprehensive Git MCP server for AI agents.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS61 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Development teams needing broad native Git CLI capabilities through MCP.
  • Local or server deployments requiring STDIO or Streamable HTTP.
  • Deployments needing working-directory restrictions, authentication, structured logging, or optional telemetry.
  • 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
  • Pure edge environments that do not provide the local Git CLI; the isomorphic-git provider is listed as planned.
  • Cloud-native GitHub API operations without a local repository; the GitHub API provider is listed only as a possible roadmap item.
  • Workflows that expect destructive cleaning or hard resets without confirmation.
  • 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
  • It needs access to and permission to modify local Git repositories and file paths within the configured scope.
  • A local Git installation is required because the current provider uses the Git CLI.
  • GPG or SSH signing setup is needed if commit signing is enabled; signing is enabled by default.
  • HTTP deployments using JWT or OAuth require the corresponding authentication secret or OIDC issuer URL.
  • 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
  • Commit, push, merge, rebase, cherry-pick, tag, and worktree operations can change repository state or remote content.
  • git clean and git reset --hard are destructive and require explicit confirmation.
  • Without GIT_BASE_DIR, operations may cover a broader accessible directory tree.
  • HTTP authentication defaults to none; authentication and access controls should be configured before public deployment.
  • If signing fails, the server silently falls back to unsigned output and reports signed and signingWarning fields.
  • 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 clientsClineClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools280