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.

DimensionAIWGA multi-agent framework for multi-platform AI-assisted software developmentNPM Sentinel MCP ServerAI-powered NPM package analysis MCP server
FMRS34 / 100 · D79 / 100 · B
Reliability3 / 2012 / 20
Security and permissions8 / 2016 / 20
Maintenance11 / 2018 / 20
Documentation8 / 2018 / 20
Setup experience4 / 2015 / 20
Best for
  • Teams that need to reuse agents, skills, commands, and rules across multiple AI coding platforms
  • Complex projects lasting weeks or months that require project memory, quality gates, and auditability
  • Developers who want to deploy plain-text AI artifacts through a CLI
  • Developers auditing NPM dependencies within AI workflows
  • Teams performing supply chain security assessments
  • Users of Claude Desktop, Cursor, or VS Code
Not for
  • Simple scripts, typo fixes, or code explanations that fit in a single conversation
  • Users who require a confirmed MCP tool list, transport protocol, or client compatibility guarantee
  • Users seeking an LLM runtime or a framework imported directly into an application
  • 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
  • Write agents, skills, rules, and context files to project- or user-level directories according to the selected platform and scope
  • Project deployments may create or update .aiwg/ and platform-specific directories
  • Optional native features may build dependencies such as node-pty or hnswlib-node
  • 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
  • Global user-scope deployment may cause context or agent sets to bleed across projects
  • The README's quantitative claims, research findings, and performance statements are not independently verified by the supplied material
  • Because the server manifest is unavailable, the MCP endpoint, tool permissions, authentication, and data-access scope cannot be confirmed
  • 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 Desktop, VS Code, Cursor
Tools019