MCP Ruby Server Skeleton

Created By
bash0C7a year ago
Experimental Ruby implementation of Model Context Protocol (MCP) - A starter server framework for trying out LLM integrations
Overview

What is MCP Ruby Server Skeleton?

MCP Ruby Server Skeleton is an experimental Ruby implementation of the Model Context Protocol (MCP), designed as a starter server framework for integrating Large Language Models (LLMs) like Claude with various tools.

How to use MCP Ruby Server Skeleton?

To use the MCP Ruby Server Skeleton, clone the repository, ensure the server script is executable, and run the server. You can also integrate it with the Claude Desktop application by modifying its configuration file.

Key features of MCP Ruby Server Skeleton?

  • Generates random integers through the get-random-number tool.
  • Compatible with MCP protocol version 2024-11-05.
  • Provides detailed logging for debugging purposes.
  • Complies with JSON-RPC 2.0 for message handling.

Use cases of MCP Ruby Server Skeleton?

  1. Integrating LLMs with custom tools for enhanced functionality.
  2. Generating random numbers for applications requiring randomness.
  3. Debugging and testing LLM integrations with detailed logs.

FAQ from MCP Ruby Server Skeleton?

  • What is the purpose of this project?

It serves as a framework for integrating LLMs with tools using the Model Context Protocol.

  • What are the requirements to run this server?

You need Ruby 3.0 or higher to run the server.

  • How can I add new tools to the server?

You can modify the RandomNumberServer class to register new tools following the provided structure.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
bash0C7
Star
0
Language
Ruby
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago