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.

DimensionSearch1API MCP ServerWeb search, news, crawling, sitemaps, and trends in one MCP server.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS67 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance16 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers who need reliable, high-quality search capabilities
  • AI applications requiring multiple search functions with easy integration
  • Remote MCP scenarios where OAuth simplifies authentication
  • 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 need fully offline or external-API-free operation
  • Scenarios where searching private data or keeping data local is required
  • High-volume crawling due to extra credit costs per crawl
  • 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 Search1API API key (local) or OAuth authorization (remote)
  • Remote mode trusts mcp.search1api.com and localhost by default; self-hosted deployments can configure MCP_ALLOWED_HOSTS and MCP_ALLOWED_ORIGINS
  • Search and crawl actions may consume API credits
  • 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
  • API key leakage: passing key via URL query parameter can expose it in logs; prefer OAuth or Authorization header
  • Network dependency: remote mode requires access to mcp.search1api.com
  • Data privacy: search queries and crawled content are sent to third-party API
  • Rate limits and costs: high-frequency requests may incur charges or be throttled
  • 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, Claude.ai, Cursor, VS Code, Claude Code, WindsurfClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools50