Streamable HTTP Transport for Web Fetch API MCP Server

@enZane

リポジトリ

基本情報

カテゴリ

生産性

ライセンス

MIT license

トランスポート

stdio

作者

enZane

Streamable HTTP Transport for Web Fetch API MCP Server について

A Stremeable Http Transport for the Model Context Protocol (MCP) suited for frameworks like Hono, enabling real-time communication using Server-Sent Events (SSE) and standard HTTP requests. Implements the MCP Streamable HTTP transport specification for edge-compatible environment

#stream-http#http-transport#real-time-communication

Streamable HTTP Transport for Web Fetch API MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Streamable HTTP Transport for Web Fetch API MCP Server のツール

For strong typing and modern JavaScript features.

For fast and reliable unit and integration testing.

For consistent code formatting and linting.

For efficient bundling of TypeScript code into CJS and ESM formats.

For streamlined version management and changelog generation.

For managing Git hooks.

概要

What is Streamable HTTP Transport for Web Fetch API?

It is an edge-compatible server transport for the Model Context Protocol (MCP) that enables real-time, bi-directional communication using Server-Sent Events (SSE) and standard HTTP requests. It is built with TypeScript and optimized for modern web frameworks like Hono and edge computing platforms.

How to use Streamable HTTP Transport for Web Fetch API?

Install the stremeable-http-transport npm package and import the EdgeStreamableHTTPTransport class. Detailed configuration and integration steps are provided in the package’s own README. The transport can be used in Node.js or edge environments supporting the Web Fetch API.

Key features of Streamable HTTP Transport for Web Fetch API

Implements the MCP Streamable HTTP transport specification.
Supports SSE streaming and direct HTTP responses.
Session management with stateful and stateless modes.
Resumability via an extensible event store.
Optimized for edge computing platforms and frameworks.
Written in TypeScript and bundled as CJS/ESM.

Use cases of Streamable HTTP Transport for Web Fetch API

Building real-time MCP servers deployed on edge runtimes.
Streaming AI model responses or tool outputs over SSE.
Enabling bi-directional communication in serverless or edge environments.
Creating MCP-compatible services with session-aware, resumable streams.

よくある質問

What runtime or frameworks does it support?

It is designed for modern edge environments and works with frameworks like Hono, as well as any runtime supporting the Web Fetch API.

Does it support session persistence?

Yes, it includes session management in both stateful and stateless modes, with resumability support via an extensible event store.

How does the transport communicate?

It uses Server-Sent Events (SSE) for streaming from server to client and standard HTTP requests for client-to-server messages, following the MCP Streamable HTTP specification.

Where can I find more detailed documentation?

Refer to the package README at `packages/stremeable-http-transport/README.md` for full configuration and API details.

What is the license?

This project is licensed under the MIT License.

「生産性」の他のコンテンツ

AccountHub

One MCP connection for all your Gmail, Google Calendar, Drive and Contacts accounts, Slack workspaces and Notion — free.

QuillHub

Meeting transcripts for AI agents: search every call, read who said what, pull decisions and action items, get quotes from one person across meetings, follow deals and projects, and transcribe files or YouTube links. Hos

QoreNext Trade Screening MCP

QoreNext

Qorenext Trade screening MCP is a Model Context Protocol server that enables Claude and other AI clients to run sanctions screening and trade-screening due-diligence directly in chat.

My AskAI

Use My AskAI to find product, setup, integration, API, feature, pricing, and troubleshooting information. Search the public knowledge base, read complete documentation and OpenAPI files, and estimate pricing from monthly

LinkedIn Ghostwriter

ContentIn

Write LinkedIn posts in your own voice from Claude, ChatGPT, or any MCP client. ContentIn trains a personal AI on your own LinkedIn posts, then generates ideas, drafts in your voice, schedules, publishes via LinkedIn's o