mcp-ts-core and mcp-starter

These two tools are competitors, with one offering a much more comprehensive and feature-rich TypeScript template for building MCP servers, while the other provides a simpler, more basic starter.

mcp-ts-core
65
Established
mcp-starter
41
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 25/25
Community 17/25
Maintenance 2/25
Adoption 7/25
Maturity 15/25
Community 17/25
Stars: 119
Forks: 20
Downloads:
Commits (30d): 0
Language: TypeScript
License: Apache-2.0
Stars: 35
Forks: 11
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
Stale 6m No Package No Dependents

About mcp-ts-core

cyanheads/mcp-ts-core

TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.

This is a framework for developers to quickly build and deploy specialized AI agent servers that perform specific tasks. It takes declarative definitions of 'tools' and 'resources' (like searching a database or greeting a user) and produces a ready-to-use server, handling common backend complexities like authentication, storage, and logging. Developers who need to create custom, task-specific AI agents without building server infrastructure from scratch would use this.

AI-agent-development backend-development developer-tools cloud-native-applications server-side-logic

About mcp-starter

instructa/mcp-starter

A super simple Starter to build your own MCP Server

This project helps developers quickly set up their own Model Context Protocol (MCP) server. It provides a basic structure to integrate local development tools like Cursor AI or Claude with the MCP standard. Developers can use this starter to create a server that processes inputs from an MCP-compatible client and outputs the results of their custom tools.

AI-tool-integration developer-workflow custom-AI-server protocol-implementation

Scores updated daily from GitHub, PyPI, and npm data. How scores work