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.

DimensionLLM ContextSmart context management for LLM development workflows.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS53 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation12 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Developers using LLM-assisted development with Claude Desktop or other MCP-supported chat interfaces.
  • Teams needing to provide precise project context to AI agents.
  • Those who want to reduce manual copy-paste and optimize token usage.
  • 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 don't need to share code with LLMs.
  • Users in environments without MCP support (though CLI is still available).
  • High-security production requiring official maintenance (this is community project).
  • 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 project files: requires access to project directory to select and read files.
  • Execute command-line operations: needs shell access for `lc-*` commands.
  • Optional clipboard access: `lc-context` copies to clipboard by default.
  • 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
  • Sensitive data leakage: shared files may contain sensitive info; choose carefully.
  • Dependency on third-party tools: requires `uvx` or `pip`; may be affected by network.
  • Misconfiguration: incorrect rules may lead to oversized or missing context.
  • 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 DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30