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.

DimensionDomain Memory AgentAn MCP server for domain-specific knowledge management with semantic search and summarization.Firecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS28 / 100 · D75 / 100 · B
Reliability4 / 2013 / 20
Security and permissions5 / 2012 / 20
Maintenance12 / 2016 / 20
Documentation3 / 2017 / 20
Setup experience4 / 2017 / 20
Best for
  • MCP users who want a lightweight, dependency-light knowledge base.
  • Cases where TF-IDF retrieval and extractive summarization are sufficient.
  • Developers exploring non-official domain knowledge servers inside the Claude Code plugin marketplace ecosystem.
  • Scenarios needing clean, structured web context fed to an AI assistant
  • Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
Not for
  • High-fidelity semantic search requiring vector/embedding retrieval or neural summarization.
  • Production knowledge platforms that need documented authentication, encryption, and access controls.
  • Users who need a complete tool catalog or official support commitments before installing.
  • Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
  • Sites that explicitly disallow automated access (robots.txt)
Required permissions
  • The source does not document an explicit permission list.
  • Because transport is stdio, the server is launched as a local process by the MCP client; actual filesystem or network access depends on the npm package implementation, which is not described in the supplied manifest.
  • Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
  • firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
Risks and side effects
  • Unofficial third-party server; it is not maintained by Anthropic, Claude Code, or the upstream product/protocol owner.
  • Installing an npm package carries normal supply-chain integrity and dependency risks.
  • The manifest does not list concrete tool names, security model, or data-handling guarantees.
  • Storage, encryption, and retention of knowledge-base data are not described in the provided materials.
  • Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
  • firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
Supported clientsClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools011