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.

DimensionPrometheus MCP ServerGive AI assistants the power to query your Prometheus metrics.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS67 / 100 · C79 / 100 · B
Reliability11 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance15 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • DevOps teams looking to integrate Prometheus metric querying into AI workflows.
  • Users who want to query metrics directly in MCP clients like Claude Desktop.
  • Scenarios requiring lightweight deployment via Docker or Helm.
  • 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 without Prometheus or MCP needs.
  • Organizations requiring official support or strict certification (this server is community-maintained).
  • High-throughput batch data extraction with low latency requirements (MCP interaction may not be suitable).
  • 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 to the Prometheus server specified by PROMETHEUS_URL.
  • Authentication credentials if Prometheus requires them (username/password or token).
  • Ability to send custom headers via PROMETHEUS_CUSTOM_HEADERS.
  • If using TLS, certificate files or SSL verification settings.
  • 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
  • Exposing Prometheus query endpoints could increase data leakage risk; ensure network access is restricted.
  • Queries may hang if timeout is not set, but the server has a default 30-second timeout.
  • Incorrect configuration can lead to authentication failures or connection errors.
  • May consume significant context tokens in MCP clients; disabling links can mitigate.
  • 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 DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools60