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.

DimensionK8M MCP 服务器管理Visually manage MCP servers and their tools inside K8MMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS44 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation8 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Teams already using K8M to manage Kubernetes clusters who want unified MCP server management
  • Users who need to connect MCP servers over SSE and want a visual on/off control
  • 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 non-SSE MCP server types (the page states these are not supported)
  • Users without a K8M deployment who just want to use a single MCP server standalone
  • 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
  • Access to the K8M admin console (login required)
  • Server read/write and delete API permissions needed to manage MCP servers
  • Once an MCP server is enabled, LLM-driven calls execute with the caller's own cluster permissions
  • 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
  • Enabled MCP servers are registered automatically in conversations and may be invoked by the model
  • The server URL is user-supplied; pointing it at an untrusted remote service risks data exposure
  • Deleting or bulk-deleting server configurations is not easily reversible
  • The default credentials k8m/k8m create a clear unauthorized-access risk if not changed promptly
  • 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 Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00