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.

DimensionUniversal Crypto MCPUniversal crypto MCP server: let AI agents operate blockchains and DeFi via natural language.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS75 / 100 · B79 / 100 · B
Reliability12 / 2012 / 20
Security and permissions16 / 2018 / 20
Maintenance15 / 2016 / 20
Documentation18 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers and analysts who want crypto market and DeFi data inside an AI client
  • MCP users wanting quick access to free market-data sources
  • Users of Claude Desktop, Cursor, or ChatGPT Developer Mode
  • 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
  • High-security scenarios requiring on-chain transactions without human review (write operations depend on PRIVATE_KEY)
  • Users seeking a server officially maintained by a blockchain platform
  • Users requiring explicit licensing guarantees (GitHub metadata shows NOASSERTION)
  • 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
  • Optional RPC_URL to connect to EVM nodes
  • Optional PRIVATE_KEY (secret) for signing transactions
  • Optional ALCHEMY_API_KEY (secret) for enhanced RPC access
  • The npm package executes third-party code via npx
  • 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
  • With PRIVATE_KEY configured, the AI agent can execute real on-chain transactions and potentially lose funds; use a dedicated hot wallet
  • Storing a private key in client environment variables risks leakage
  • npx automatically executes third-party code from npm, a supply-chain risk
  • License metadata is NOASSERTION on GitHub; verify terms before commercial use
  • Many advertised capabilities (e.g., 380+ tools, multi-chain operations) belong to sibling packages in the monorepo and may not be part of this server. server
  • 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, Cursor, ChatGPT Developer ModeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools110