anthropics / anthropics/claude-ai-mcp

Elicitation Support

Aperta
#153 11 commenti 40 reazioni 1 assegnatario Rivendicata da @ochafik Vedi su GitHub
enhancement
Lingua principale
Nessun dato sulla lingua
Stelle
471
Fork
77
Metriche di merge delle PR
Nessuna PR unita negli ultimi 30g

Descrizione

### Problem Statement

With [Elicitation](https://modelcontextprotocol.io/specification/2025-11-25/client/elicitation) now supported in Claude Code, support in Claude.ai as well would help finally make this feature of the spec something MCP server developers could rely on.

Elicitation would enable significantly cleaner and more reliable user experiences for several workflows we're looking to implement - experiences that conversational interaction alone cannot match. Certain user inputs, such as confirming high-risk actions, benefit greatly from the structured, focused prompts that elicitation provides, rather than being included in open-ended dialogue.

### Proposed Solution

Add [the elicitation functionality of the MCP spec](https://modelcontextprotocol.io/specification/2025-11-25/client/elicitation) to Claude.ai.

### Area

Protocol Support

### Priority

High - Major improvement needed

Guida per i contributori

Nessuna guida per i contributori indicizzata per questo repository

Valutazione

Questa issue non è ancora stata valutata.

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.