[{"data":1,"prerenderedAt":70},["ShallowReactive",2],{"term-e\u002Felicitation":3,"related-e\u002Felicitation":58},{"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":52,"sitemap":53,"stem":56,"subcategory":6,"__hash__":57},"terms\u002Fterms\u002Fe\u002Felicitation.md","Elicitation",null,{"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",{},"Elicitation is the MCP pattern where a tool pauses mid-task to ask you clarifying questions — the AI learned to ask before guessing. Instead of charging ahead and implementing the wrong thing confidently, the tool surfaces a form or prompt: \"Which database should I use?\" \"Should this be public or authenticated?\" It's the difference between an assistant who clarifies ambiguity and one who figures it out themselves and gets it wrong spectacularly.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"In the Model Context Protocol spec, elicitation is a server-to-client request where an MCP server asks the host (and by extension the user) for additional information mid-operation. The server sends a structured schema describing what data it needs; the host renders a UI or prompt to collect it. This enables interactive MCP tools that can handle ambiguous tasks without hardcoding assumptions or failing silently on missing inputs.",[11,27,29],{"id":28},"when-youll-hear-this","When You'll Hear This",[16,31,32],{},"\"The MCP server uses elicitation to ask which environment to target before deploying.\" \u002F \"Elicitation makes the tool feel interactive instead of fire-and-forget.\"",{"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","Elicitation is the MCP pattern where a tool pauses mid-task to ask you clarifying questions — the AI learned to ask before guessing.","intermediate","md","e",{},true,"\u002Fterms\u002Fe\u002Felicitation",[49,50,51],"MCP","Agent","Tool Use",{"title":5,"description":41},{"changefreq":54,"priority":55},"weekly",0.7,"terms\u002Fe\u002Felicitation","UTOpQAKu1G9jyBID8rxczMDcMcEDypIXn5TNoZLl3VM",[59,62,67],{"title":50,"path":60,"acronym":6,"category":40,"difficulty":42,"description":61},"\u002Fterms\u002Fa\u002Fagent","An AI agent is an LLM that doesn't just answer questions — it takes actions.",{"title":49,"path":63,"acronym":64,"category":65,"difficulty":42,"description":66},"\u002Fterms\u002Fm\u002Fmcp","Model Context Protocol","vibecoding","MCP is like USB for AI — a universal standard for connecting AI models to external tools and data.",{"title":51,"path":68,"acronym":6,"category":40,"difficulty":42,"description":69},"\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.",1775560896656]