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.

DimensionGrowthBook MCP ServerOfficial GrowthBook MCP server: skill loader + authenticated API passthroughMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS60 / 100 · C79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions9 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation16 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Teams already using GrowthBook who want agents to manage flags and experiments
  • MCP users who want an authenticated, auditable API passthrough
  • Operators of self-hosted instances
  • 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 GrowthBook
  • Read-only browsing without a GrowthBook API key
  • Environments that cannot tolerate agent-driven mutating API calls
  • 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
  • GB_API_KEY: a GrowthBook API key or personal access token (required, secret)
  • GB_API_URL: API base URL (optional, defaults to https://api.growthbook.io)
  • GB_HTTP_HEADER_*: extra request headers (e.g. Cloudflare Access tokens)
  • 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
  • growthbook_call_api is a generic passthrough; POST/PUT/PATCH/DELETE can mutate data, and the confirm-with-user rule is soft guidance, not a hard gate
  • The API key is a sensitive credential that can act on the whole account if leaked
  • HTTP mode should run on a trusted network or loopback; multi-tenant or public deployments should be fronted by your own gateway/auth
  • 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
Tools30