Skip to main content
Glama
MCP Elicitations Demo Server

MCP Elicitations Demo Server

by soriat

MCP Everything Server

A comprehensive reference implementation for the Model Context Protocol (MCP) that demonstrates all features of the protocol. This server showcases the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.

This server is built with the TypeScript MCP SDK.

Features

This server implements a comprehensive set of MCP features including:

  • Tools: Various tools including echo, add, long-running operations, environment variable printing, LLM sampling, and more

  • Prompts: Simple and complex prompts with arguments, resource references, and embedded content

  • Resources: Static resources with pagination support, resource templates, and subscriptions

  • Logging: Configurable logging levels with real-time notifications

  • Completions: Auto-completion for prompt arguments and resource references

  • Elicitation: Interactive user input collection with structured schemas

  • Annotations: Content annotations for priority and audience targeting

  • Progress Tracking: Progress notifications for long-running operations

  • Real-time Updates: Resource update notifications and stderr streaming

Related MCP server: Basic MCP Server

Installation

npm install -g @modelcontextprotocol/server-everything

Usage

Standard I/O

mcp-server-everything

Server-Sent Events (SSE)

npm run start:sse

HTTP with Streaming Support

npm run start:streamableHttp

Development

  1. Clone the repository:

git clone https://github.com/modelcontextprotocol/servers.git
cd servers
  1. Install dependencies:

npm install
  1. Build the server:

npm run build
  1. Run the server:

npm start

Configuration

The server supports various configuration options and can be used to test and demonstrate MCP capabilities. It includes:

  • 100 static resources (mix of text and binary)

  • Multiple tool implementations

  • Various prompt templates

  • Real-time notifications and updates

  • Progress tracking for long operations

Docker

Build and run with Docker:

docker build -t mcp-everything-server .
docker run -p 3000:3000 mcp-everything-server

License

MIT - See LICENSE file for details.

Contributing

See CONTRIBUTING.md for contribution guidelines.

Available Tools

10 tools
addB

Adds two numbers

Inputs: a (required), b (required).

annotatedMessageC

Demonstrates how annotations can be used to provide metadata about content

Inputs: messageType (required), includeImage.

echoB

Echoes back the input!

Inputs: message (required).

getResourceReferenceC

Returns a resource reference that can be used by MCP clients

Inputs: resourceId (required).

getTinyImageC

Returns the MCP_TINY_IMAGE

Inputs: no named parameters.

longRunningOperationC

Demonstrates a long running operation with progress updates

Inputs: duration, steps.

printEnvA

Prints all environment variables, helpful for debugging MCP server configuration

Inputs: no named parameters.

sampleLLMC

Samples from an LLM using MCP's sampling feature

Inputs: prompt (required), maxTokens.

startElicitationB

Demonstrates the Elicitation feature by asking the user to provide information about their favorite color, number, and pets.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.8/5.0

    Scored across 10 tools

    Disambiguation3/5

    The tools have distinct technical purposes, but there is some functional overlap in the demonstration category. For example, 'annotatedMessage', 'longRunningOperation', 'sampleLLM', and 'startElicitation' all serve as MCP feature demos, which could cause confusion about which to use for general demonstration tasks. However, their specific descriptions help differentiate them.

    Naming Consistency2/5

    The naming conventions are inconsistent, mixing verb-first (e.g., 'add', 'echo', 'printEnv'), noun-first (e.g., 'annotatedMessage'), and descriptive phrases (e.g., 'longRunningOperation', 'getResourceLinks'). There is no uniform pattern like verb_noun or camelCase throughout, making the set less predictable.

    Tool Count4/5

    With 10 tools, the count is reasonable for a demo server showcasing various MCP features. It is well-scoped to demonstrate capabilities without being overwhelming, though it might feel slightly heavy if the purpose is purely educational rather than functional.

    Completeness5/5

    As a demo server, the tool set comprehensively covers the intended domain of MCP feature demonstrations, including basic operations, resource handling, long-running tasks, LLM sampling, and elicitations. There are no obvious gaps for its stated purpose of showcasing MCP functionalities.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A demonstration server showing MCP implementation in Python with resource handling, tool operations, and reusable prompts for a simple user/post system with local database.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      A minimal demonstration server showcasing MCP protocol capabilities including tools, resources, and prompts with basic examples like hello world functionality.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A demonstration server designed to showcase core Model Context Protocol (MCP) primitives including tools, resources, and prompts for presentations. It provides functional examples like text analysis and financial calculations to illustrate how AI models interact with external functions and data.
      5
      -
    • A
      license
      B
      quality
      D
      maintenance
      A toy MCP server for exploring Model Context Protocol capabilities, including resources, tools, and prompts.
      1
      Apache 2.0