MCP Elicitations Demo Server

A demonstration server that showcases elicitations across different Model Context Protocol (MCP) use cases. This server demonstrates how to collect user input dynamically using the MCP elicitation system.

What are Elicitations?

Elicitations allow MCP servers to request structured input from users during tool execution, enabling interactive and dynamic workflows.

Available MCP Components

Tools

  • greeting - Simple greeting tool that asks for your name
  • contact-info - Collects structured contact information (name, email, age)

Resources

  • config://user - User greeting resource that dynamically requests your name

Prompts

  • greeting-prompt - Generates a personalized greeting prompt based on your name

How It Works

Each component demonstrates elicitations in different contexts:

  1. Tools show how to collect input during tool execution
  2. Resources demonstrate dynamic content generation based on user input
  3. Prompts showcase how to create personalized prompts using elicited data

Running the Server

npm install
npm run build
npm start

The server will run on http://localhost:3000

Example Elicitation Schemas

Simple Name Request

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "The name of the user"
    }
  },
  "required": ["name"]
}

Contact Information Request

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Your full name"
    },
    "email": {
      "type": "string",
      "format": "email", 
      "description": "Your email address"
    },
    "age": {
      "type": "number",
      "minimum": 18,
      "description": "Your age"
    }
  },
  "required": ["name", "email"]
}

This demo showcases MCP elicitations for creating interactive, user-driven experiences across tools, resources, and prompts.

MCP Server ยท Populars

MCP Server ยท New

    LeulAria

    Aria Icons

    MCP server for 340k SVG icons

    Community LeulAria
    knowall-ai

    Reverie โ€” graph memory that dreams

    Memory management MCP server for AI agents using Neo4j knowledge graphs

    Community knowall-ai
    keploy

    Key Highlights

    Open-source platform for creating safe, isolated production sandboxes for API, integration, and E2E testing.

    Community keploy
    hermes-labs-ai

    Fidelis Memory

    Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. MIT.

    Community hermes-labs-ai
    n24q02m

    Better Code Review Graph

    Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

    Community n24q02m