MCP Servers
63,654 MCP servers for AI apps. Filter by category, badge and popularity.
Data & Analytics
Academic commercialization intelligence for AI agents via the Model Context Protocol. This MCP server orchestrates 8 academic and patent data sources — OpenAlex, Semantic Scholar, ArXiv, USPTO, EPO, NIH Grants, Grants.gov, and ClinicalTrials
Academic research technology scouting, university tech transfer intelligence, and lab profiling — delivered as an MCP server your AI agent calls directly. Connect to 8 live academic databases simultaneously: OpenAlex, ArXiv, USPTO, EPO, NIH, Grants
An intelligent customer service RAG server based on Model Context Protocol (MCP). This tool allows AI clients (such as Cursor and Claude Desktop) to directly retrieve operation guides, FAQs, and visitor information from the knowledge base through standardized tool calls. It features strict accuracy safeguards and honestly informs when data is not found, ensuring 100% accuracy in AI customer service responses.
AgenticBI is an agentic analytics platform that turns business questions into answers. Connect BigQuery, Salesforce, SAP, Google Drive, Trino, and more. Agents understand your data, find the right datasets, join across systems, run queries, and return answers with visualizations
MCP server for Canadian real estate agents. 16 read-only tools covering transactions, pipeline deals, CRM clients, expenses, mileage tracking, income forecasts, Runway Score (business health grade), and Canadian income tax estimates for all 13 provinces/territories. Streamable HTTP.
AI training data quality assessment, bias detection, and governance scoring — delivered to any MCP-compatible AI agent through a single always-on server. This server orchestrates 7 specialized data sources (dataset registries, GitHub, ArXiv, Semantic Scholar, Hacker News, Wikiped
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.
