What runtimes does the template support?
It supports Bun (v1.3.0+), Node.js, and Cloudflare Workers. Scaffolded projects can use either the standard `createApp()` or `createWorkerHandler()` for Workers.
@cyanheads
基本信息
Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-ts-template": {
"command": "bun",
"args": [
"run",
"rebuild",
"#",
"clean",
"+",
"build",
"(scripts/clean.ts",
"+",
"scripts/build.ts)"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
The MCP TypeScript Template is an agent-native TypeScript framework and starter project for building MCP servers. It provides declarative tool, resource, and prompt definitions with built-in auth, multi-backend storage, OpenTelemetry observability, and first-class support for Bun, Node.js, and Cloudflare Workers. It is designed to let developers focus on domain logic while the framework handles infrastructure.
Run bunx @cyanheads/mcp-ts-core init my-mcp-server to scaffold a new project, then cd my-mcp-server && bun install. Use the tool(), resource(), and prompt() builders to define your server’s capabilities and call createApp() in the entry point. Configuration is done via environment variables.
It supports Bun (v1.3.0+), Node.js, and Cloudflare Workers. Scaffolded projects can use either the standard `createApp()` or `createWorkerHandler()` for Workers.
Transports: `stdio` (default) and `http` (port configurable via `MCP_HTTP_PORT`). Auth modes: `none`, `jwt`, or `oauth` (configured with `MCP_AUTH_MODE` and related variables).
Storage providers: `in‑memory` (default), `filesystem`, `supabase`, `cloudflare‑d1`, `cloudflare‑kv`, and `cloudflare‑r2`. Switch via the `STORAGE_PROVIDER_TYPE` env var.
Use the `tool()` builder with a Zod `output` schema. Structured content is available to clients that support it. Add a `format()` method to render markdown for clients that only read `content[]`. A linter (run via `lint:mcp`) checks parity between the two surfaces.
Yes. The framework provides `createWorkerHandler()`, which returns an `ExportedHandler`. Use the same tool, resource, and prompt definitions — only the entry point differs.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
评论