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.

DimensionDeepSeek MCP ServerCommunity MCP server for DeepSeek V4 with chat, reasoning, function calling, and cost tracking.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS63 / 100 · C79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation17 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers using MCP clients such as Claude Code, Gemini CLI, Cursor, or Windsurf
  • Users who want DeepSeek V4 models inside their local agent tooling
  • Teams that need cost tracking and usage statistics
  • Users wanting a hosted BYOK endpoint with no installation
  • 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 seeking official DeepSeek support channels (this is community-maintained)
  • Users without a DeepSeek API key
  • Users needing other LLM providers such as OpenAI or Anthropic
  • 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
  • DEEPSEEK_API_KEY environment variable (secret) is required
  • API usage costs billed via your DeepSeek API key
  • Self-hosted HTTP mode requires an open network port (binds 127.0.0.1 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
  • If the HTTP endpoint is exposed, anyone who can reach POST /mcp can spend your API key; set HTTP_AUTH_TOKEN when binding 0.0.0.0
  • Thinking mode can exceed 30 seconds and client tool-call timeouts may interrupt long requests
  • Costs accrue per request and grow with usage
  • Deprecated model aliases deepseek-chat/deepseek-reasoner will be removed in the next major release
  • 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, Gemini CLI, Cursor, Windsurf, VS CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30