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.

DimensionSSH Manager MCP ServerSSH remote server management via Model Context ProtocolNPM Sentinel MCP ServerAI-powered NPM package analysis MCP server
FMRS52 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions9 / 2016 / 20
Maintenance11 / 2018 / 20
Documentation15 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers and DevOps engineers using Claude Code or OpenAI Codex
  • Teams managing multiple servers who want to automate routine tasks
  • Sysadmins needing quick command execution, file transfer, or monitoring
  • Developers auditing NPM dependencies within AI workflows
  • Teams performing supply chain security assessments
  • Users of Claude Desktop, Cursor, or VS Code
Not for
  • Non-technical users, as SSH and command-line basics are required
  • Highly security-sensitive environments if misconfigured, as SSH credentials exposure is a risk
  • Use cases requiring agent installation on each server, as this uses direct SSH
  • Projects outside the NPM ecosystem (e.g., pure Python/Go)
  • Environments without network access to deps.dev, OSV.dev, and the npm registry
  • Scenarios requiring maintenance by an official upstream vendor
Required permissions
  • Access to local SSH config and credentials (passwords, keys, ssh-agent)
  • Ability to execute remote commands, transfer files, manage databases and backups
  • Ability to create SSH tunnels and persistent sessions
  • Ability to read and modify local .env and TOML configuration files
  • Network access to the NPM registry and external services (deps.dev, OSV.dev, OpenSSF, npms.io, GitHub)
  • Read access to workspace lockfiles (pnpm-lock.yaml, package-lock., yarn.lock) for cache invalidation
Risks and side effects
  • Credentials may be stored in plaintext in config files, posing security risks if files are compromised
  • Executing arbitrary commands via ssh_execute can cause unintended changes or damage
  • SSH agent forwarding can expose local keys to remote hosts if used with excessive permissions
  • Unstable network connections may lead to command timeouts or failures
  • Third-party READMEs and changelogs are untrusted external content; they are wrapped in tags with _meta flags but should still be handled cautiously
  • Depends on availability and accuracy of external services
  • Batch requests are capped at 25 packages to prevent registry enumeration; larger sets require batching
  • Third-party open source project, not officially maintained by NPM or Anthropic
Supported clientsClaude Code, CodexClaude Desktop, VS Code, Cursor
Tools3619