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.

DimensionDecodo MCP ServerEnable your AI agents to scrape and parse web content dynamically, including geo-restricted sitesNPM Sentinel MCP ServerAI-powered NPM package analysis MCP server
FMRS57 / 100 · C79 / 100 · B
Reliability7 / 2012 / 20
Security and permissions12 / 2016 / 20
Maintenance9 / 2018 / 20
Documentation16 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers who need real-time web data for LLMs and RAG pipelines
  • Teams building eCommerce intelligence, social monitoring, or price aggregation tools
  • AI agent projects that want production scraping without maintaining proxy infrastructure
  • Developers auditing NPM dependencies within AI workflows
  • Teams performing supply chain security assessments
  • Users of Claude Desktop, Cursor, or VS Code
Not for
  • Users who cannot rely on a third-party paid scraping service or hosted endpoint
  • Workflows needing only local file or internal data access
  • Privacy-sensitive cases where sending target URLs and prompts to Decodo's servers is unacceptable
  • 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
  • Requires a Decodo Web Scraping API basic auth token (SCRAPER_API_TOKEN)
  • Downloads and runs the @decodo/mcp-server package via npx from npm
  • Requires network access to call Decodo's hosted scraping service
  • 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
  • All target URLs and prompts pass through a third-party (Decodo) server
  • API usage costs apply once the free quota is exhausted
  • Scraping target sites may violate their terms of service; verify compliance yourself
  • Dependency on an external npm package and hosted API introduces supply-chain and availability risks
  • 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, Cursor, Windsurf, Claude CodeClaude Desktop, VS Code, Cursor
Tools3019