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.

DimensionQuickBooks Online MCP ServerAccess QuickBooks Online data and accounting operations through MCP.Firecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS32 / 100 · D75 / 100 · B
Reliability4 / 2013 / 20
Security and permissions7 / 2012 / 20
Maintenance6 / 2016 / 20
Documentation8 / 2017 / 20
Setup experience7 / 2017 / 20
Best for
  • Developers integrating QuickBooks Online data or accounting operations
  • Local integrations using Claude Code or another MCP-compatible client
  • Teams needing sandbox testing or production company access
  • 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
  • Users who do not use QuickBooks Online
  • Users unable to register an Intuit app and complete OAuth authorization
  • Teams seeking a hosted service without a local process or credential configuration
  • 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
  • Requires Intuit OAuth 2.0 app credentials
  • Requires access to a QuickBooks Online company and its Realm ID
  • Depending on enabled tools, may require permission to read, create, update, and delete accounting data
  • 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
  • Write, update, and delete tools can change or void accounting records
  • Refresh tokens rotate automatically and are written back to a configuration file
  • Initial production OAuth authorization requires a public HTTPS callback
  • The source contains conflicting license information: Apache-2.0 in repository metadata and MIT in the README
  • 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 CodeClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools10011