MCP TypeScript Simple Template

Created By
ChenReuvena year ago
A lightweight, ready-to-use TypeScript template for building Model Context Protocol (MCP) servers. This template provides the essential scaffolding to create custom AI tools that can be seamlessly integrated with large language models.
Overview

what is MCP TypeScript Simple Template?

MCP TypeScript Simple Template is a lightweight TypeScript template designed for building Model Context Protocol (MCP) servers, providing essential scaffolding for creating custom AI tools that integrate with large language models.

how to use MCP TypeScript Simple Template?

To use this template, clone the repository, install the dependencies, and run the server using npm commands. You can modify the index.ts file to add your own tools.

key features of MCP TypeScript Simple Template?

  • Basic implementation of an MCP server with a sample BMI calculator tool.
  • Input validation for tools using Zod.
  • Easy integration with standard I/O for communication.

use cases of MCP TypeScript Simple Template?

  1. Building custom AI tools that utilize the Model Context Protocol.
  2. Creating interactive applications that require server-client communication.
  3. Developing educational tools that can be integrated with AI systems.

FAQ from MCP TypeScript Simple Template?

  • What are the prerequisites for using this template?

You need Node.js (v20 or higher) and npm or yarn installed.

  • How do I create a new tool?

Follow the provided pattern in index.ts to define your tool and its input schema using Zod.

  • Is this template suitable for production use?

This template is a starting point and may require additional modifications for production readiness.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
ChenReuven
Star
0
Language
TypeScript
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)

9 hours ago