[{"data":1,"prerenderedAt":74},["ShallowReactive",2],{"term-m\u002Fmodel-context-protocol":3,"related-m\u002Fmodel-context-protocol":61},{"id":4,"title":5,"acronym":6,"body":7,"category":40,"description":41,"difficulty":42,"extension":43,"letter":44,"meta":45,"navigation":46,"path":47,"related":48,"seo":54,"sitemap":55,"stem":58,"subcategory":59,"__hash__":60},"terms\u002Fterms\u002Fm\u002Fmodel-context-protocol.md","Model Context Protocol","MCP",{"type":8,"value":9,"toc":33},"minimark",[10,15,19,23,26,30],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 — The Vibe Check",[16,17,18],"p",{},"MCP is a standard protocol that lets AI assistants connect to external tools and data sources — like a universal adapter for AI. Instead of every AI tool building custom integrations for GitHub, Slack, databases, etc., MCP provides one standard interface. Build an MCP server once, and any MCP-compatible AI client can use it. It's like USB but for AI tool connections.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"Model Context Protocol (MCP) is an open standard developed by Anthropic that defines how AI applications connect to external data sources and tools. It uses a client-server architecture where AI hosts (Claude, IDEs, custom agents) connect to MCP servers that expose resources, tools, and prompts. MCP servers can provide file access, database queries, API integrations, and more through a standardized JSON-RPC interface. It enables composable AI tool ecosystems.",[11,27,29],{"id":28},"when-youll-hear-this","When You'll Hear This",[16,31,32],{},"\"We built an MCP server for our internal API so Claude can query it directly.\" \u002F \"MCP means we write one integration that works with Claude, Cursor, and any other MCP client.\"",{"title":34,"searchDepth":35,"depth":35,"links":36},"",2,[37,38,39],{"id":13,"depth":35,"text":14},{"id":21,"depth":35,"text":22},{"id":28,"depth":35,"text":29},"ai","MCP is a standard protocol that lets AI assistants connect to external tools and data sources — like a universal adapter for AI.","intermediate","md","m",{},true,"\u002Fterms\u002Fm\u002Fmodel-context-protocol",[49,50,51,52,53],"AI Agent","Tool Use","Claude","API","Integration",{"title":5,"description":41},{"changefreq":56,"priority":57},"weekly",0.7,"terms\u002Fm\u002Fmodel-context-protocol",null,"dBGnPBI-JKtCVPbwGGSUR2F9WdaYhbtbNhlFJcFZ7z8",[62,65,71],{"title":49,"path":63,"acronym":59,"category":40,"difficulty":42,"description":64},"\u002Fterms\u002Fa\u002Fai-agent","An AI Agent is an AI system that can think, plan, and act on its own to accomplish a goal.",{"title":52,"path":66,"acronym":67,"category":68,"difficulty":69,"description":70},"\u002Fterms\u002Fa\u002Fapi","Application Programming Interface","backend","beginner","An API is like a menu at a restaurant. The kitchen (server) can do a bunch of things, but you can only order what's on the menu.",{"title":50,"path":72,"acronym":59,"category":40,"difficulty":42,"description":73},"\u002Fterms\u002Ft\u002Ftool-use","Tool use is when an AI can call external functions, APIs, or programs to do things it can't do alone.",1776518295729]