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.

DimensionBrowserStack MCP ServerBrowserStack's official MCP server for natural language control of the test platform.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS40 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation8 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • QA teams using BrowserStack
  • Developers who want to integrate testing into AI workflows
  • Teams needing accessibility compliance
  • Automated test maintenance
  • 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
  • Teams not using BrowserStack
  • Users needing local testing support (Remote MCP cannot access localhost)
  • Users expecting fully automated file modifications (tools only suggest fixes)
  • 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 BrowserStack username and access key
  • Can create and modify Test Management projects, test cases, and runs
  • Can start live sessions and run automated tests
  • Can access test reports and logs
  • Some tools require access to local file system (e.g., uploading files)
  • 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
  • Credentials may be logged by tools; handle them securely
  • AI might produce unexpected actions; test in a safe environment
  • Some tools are unavailable in Remote MCP, behavior may differ
  • Test execution may incur costs
  • Dependency on network and BrowserStack service availability
  • 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, GitHub Copilot, Cursor, ClineClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools440