frontmcp
TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
claude mcp add --transport stdio agentfront-frontmcp npx -y frontmcp
How to use
FrontMCP is a TypeScript-first framework for building MCP servers with decorators, dependency injection, and a streamable HTTP transport. It provides a structured approach to defining servers, apps, tools, resources, prompts, and agents, while handling protocol negotiation, sessions, authentication, and execution flow. The readme emphasizes a decorator-driven configuration model and a focus on typed development, making it easier to compose complex MCP capabilities like UI widgets, tool manifests, and extensible workflows. The toolkit centers around the @FrontMcp decorator, modular building blocks (Apps, Tools, Resources, Prompts, Agents), and a transport layer that supports HTTP streaming and session headers.
To start, you install the FrontMCP CLI tooling and scaffold a project with commands such as npx frontmcp create my-app or initialize an existing project with npx frontmcp init. Once set up, you define your server class using the FrontMCP decorator, configure HTTP ports, logging levels, and the apps/tools you want to expose. The framework then handles the MCP protocol, DI, and the runtime flow, letting you focus on business logic and tool orchestration.
How to install
Prerequisites:
- Node.js 22+ (24 recommended)
- A supported shell/terminal
Install steps:
- Create a new project with the FrontMCP CLI (recommended):
npx frontmcp create my-app
- For an existing project, install the core package and types, then initialize the project scaffold:
npm i -D frontmcp @types/node@^22
npx frontmcp init
- Start the development server (typical workflow):
npm run dev
- Refer to the official docs for deployment and production build steps, as applicable to your environment.
Additional notes
Notes and tips:
- Ensure your environment uses Node.js 22+; Node 24 is recommended for compatibility with the latest features.
- Keep all @frontmcp/* packages on the same version to avoid version drift errors during boot.
- The CLI provides commands like create, init, dev, and build to streamline project setup and deployment.
- If you encounter issues, consult the MCP docs pages linked in the readme, such as Server, Apps, Tools, and others, for API references and troubleshooting.
- The framework emphasizes typed schemas (e.g., using Zod for Tools) to improve reliability and developer experience.
Related MCP Servers
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
shinzo-ts
TypeScript SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
mcp-bun
Bun Javascript Runtime MCP Server for AI Agents