MCP Servers
69,837 MCP servers for AI apps. Filter by category, badge and popularity.
All
This MCP server uses the Fresh LinkedIn Profile Data API to fetch LinkedIn profile information. It is implemented as a model context protocol (MCP) server and exposes a single tool, get_profile, which accepts a LinkedIn profile URL and returns the profile data in JSON format.
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP server for LinkedIn (beta): https://www.cdata.com/download/download.aspx?sku=CLZK-V&type=beta
Memory consolidation across vendors, owners, and time. Lithtrix gives AI agents persistent memory, credibility-scored web search, browser fetch, and a shared commons pool — all under a stable ltx_ key that survives tool switches, session resets, and orchestrator changes.
Connect Claude, Cursor, Windsurf and other AI assistants directly to your live Meta Ads, Google Analytics 4, and Google Search Console accounts. Ask natural language questions and get real answers from your actual data — no CSV exports, no tab switching.
Chinese perpetual calendar MCP server. Supports Gregorian-lunar calendar conversion, 24 solar terms, statutory holidays, auspiciousness and taboos, eight characters and five elements, and auspicious date queries. 9 tools in total, directly integrated with Claude/Cursor.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
