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.

DimensionScira MCP ChatOpen-source AI chatbot app powered by Model Context ProtocolMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS36 / 100 · D79 / 100 · B
Reliability7 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation7 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Developers seeking a customizable, open-source MCP client framework
  • AI app builders who want to leverage tools from multiple MCP servers
  • Projects needing modern React UI components and streaming responses
  • 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 needing a production-grade, fully hosted MCP client solution
  • Users who need to run MCP servers locally via stdio (client supports only HTTP and SSE)
  • Non-technical users as it requires development deployment
  • 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
  • Network access: Connects to MCP servers via HTTP or SSE
  • System access: Requires basic system resources to run as a Next.js app
  • Users typically need to configure API keys for AI providers
  • 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
  • Connecting to untrusted MCP servers may introduce malicious tools
  • Stored API keys may be at risk if environment is insecure
  • As an open-source project, there may be unpatched vulnerabilities
  • 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, Generic MCP ClientClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools10