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.

DimensionConversational API DebuggerDebug REST API failures using OpenAPI specs and HTTP logs, with conversational root-cause analysis and cURL generation.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS20 / 100 · D79 / 100 · B
Reliability2 / 2012 / 20
Security and permissions4 / 2018 / 20
Maintenance9 / 2016 / 20
Documentation2 / 2018 / 20
Setup experience3 / 2015 / 20
Best for
  • Claude Code users who want an assistant-oriented debugger for REST API failures.
  • Teams that have OpenAPI specs and HTTP/HAR logs and need structured root-cause analysis.
  • Developer workflows that prefer conversational iteration over paging through raw logs.
  • 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
  • Non-REST debugging — the server is scoped to REST API failures via OpenAPI specs and HTTP logs; no support for other protocols is documented.
  • Replacing observability/APM platforms or automated test runners — only the documented debugging workflow is evidenced.
  • Users who need a known, enumerated list of tool names — the source material does not document the server's tool identifiers.
  • 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
  • Read access to the OpenAPI spec files and HTTP/HAR logs it is asked to analyze.
  • A Node.js runtime able to run the npm package as a stdio child process of Claude Code.
  • Whatever filesystem and environment access Claude Code grants the plugin during the session.
  • 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
  • Community-maintained rather than an official Anthropic or upstream-vendor server; verify conclusions before acting.
  • Analysis quality depends on the accuracy and completeness of the provided OpenAPI specs and logs.
  • Generated cURL commands should be reviewed before execution to avoid unintended side effects.
  • 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 CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00