http-mcp-server

http-mcp-server

Mock HTTP server implementing MCP (Model Context Protocol) with streamable HTTP transport, health endpoint, and example tools like echo and time.

Category
访问服务器

README

MCP Mock HTTP

Mock HTTP server for MCP-style clients.

Quick path

  1. Put PORT and MCP_NAME in .env at the repo root.
  2. Run pnpm dev or pnpm start.
  3. Open http://localhost:<PORT>/health or connect a client to http://localhost:<PORT>/mcp.

Runtime configuration

Source Behavior
.env in the repo root Loaded by src/server.ts before env parsing
Shell environment Takes precedence over .env values
src/config/env.ts Validates PORT and MCP_NAME, then applies defaults
Variable Default Purpose
PORT 3000 HTTP listen port
MCP_NAME mcp-mock MCP server name and health payload name

Versioning

Source Purpose
package.json Single source of truth for the server version
src/version.ts Runtime accessor used by the MCP server and tests
CHANGELOG.md Repository-level release tracking

When reusing this repository as a base for another MCP server, update the package version and add a changelog entry before the first release.

Requirements

  • Node.js 26.0.0
  • pnpm

Install

pnpm install

Run

pnpm dev

The server bootstrap loads .env automatically, so local values apply without exporting them in the shell.

Build

pnpm build

Docker

Build the production image:

docker build -t mcp-server .

Run it with runtime environment variables:

docker run --rm -p 3000:3000 --env-file .env mcp-server

Override values at runtime when needed:

docker run --rm -p 3000:3000 -e PORT=8080 -e MCP_NAME=my-mcp mcp-server

The image does not contain your .env file. That keeps secrets out of the image while still letting the server read .env-style values if you provide them at runtime.

Quality checks

pnpm typecheck
pnpm lint
pnpm test
pnpm coverage
pnpm format

pnpm coverage runs Vitest with the v8 coverage provider and prints a coverage summary in the terminal.

Endpoints

  • GET /health — JSON health response with ok, name, and uptime.
  • /mcp* — MCP streamable HTTP transport handled by the SDK bridge.

MCP Inspector

Use the Inspector as a client against the running HTTP server:

  1. Start this project.

  2. Launch the Inspector:

    npx @modelcontextprotocol/inspector
    
  3. In the Inspector, choose the Streamable HTTP transport and connect to http://localhost:<PORT>/mcp.

  4. Verify the connection by listing tools or calling one of the registered tools.

Project structure

  • src/server.ts — process bootstrap only
  • src/app.ts — HTTP server composition and routing
  • src/config/env.ts — environment parsing and validation
  • src/http/routes/health.ts — health route handler
  • src/mcp/create-server.ts — MCP server construction and tool registration
  • src/version.ts — runtime version resolution from package.json
  • src/mcp/tools/echo.ts — echo tool registration
  • src/mcp/tools/time.ts — time tool registration
  • src/mcp/transport.ts — Node HTTP to MCP transport bridge

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选