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.

DimensionBlockscout MCP ServerExposes Blockscout blockchain data via MCPMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS66 / 100 · C79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions14 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation18 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • AI agents and IDE users needing real-time multi-chain blockchain data
  • Blockchain analysts and developers
  • Crypto researchers using Claude, Cursor, ChatGPT, or Codex
  • 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 unwilling to register for a Blockscout PRO API key
  • Scenarios requiring on-chain writes or signing (all tools are read-only queries)
  • Telemetry-sensitive users running community instances without disabling telemetry
  • 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 a Blockscout PRO API key (proapi_ prefix) for data access
  • Accesses https://mcp.blockscout.com/mcp over HTTP transport
  • Self-hosted deployments provide the key via the BLOCKSCOUT_PRO_API_KEY environment variable
  • 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
  • PRO API access is metered in credits; tools append advisory notes when the balance drops below a threshold
  • Community instances collect anonymous telemetry by default (tool names, parameters, version, SHA-256 hash of the API key); disable with BLOCKSCOUT_DISABLE_COMMUNITY_TELEMETRY=true
  • The PRO API key must never be committed to version control or embedded in client-shipped binaries
  • Claude Connectors Directory requires a paid Claude plan and may have restrictions due to a shared access key
  • 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 Code, Claude (Web) Connectors Directory, ChatGPT Apps, Codex, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools160