McpHub
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@McpHubList all capabilities from every connected MCP server."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
McpHub
MCP bridge -- folds the capabilities (tools / prompts / resources) of multiple MCP servers into 4 fixed tools, exposed uniformly to AI tools.
Quick Start
stdio mode (default)
dotnet run --project src/McpHub -- --config examples/mcp-hub.config.jsonConfigure in your AI tool's mcp.json:
{
"servers": {
"mcp-hub": {
"command": "dotnet",
"args": [
"run",
"--project", "path/to/McpHub",
"--", "--config", "path/to/mcp-hub.config.json"
]
}
}
}HTTP mode
dotnet run --project src/McpHub -- --http --port 8080 --config examples/mcp-hub.config.jsonClient connects to http://localhost:8080/ (Streamable HTTP).
Related MCP server: MCP Inspector as MCP Server
CLI Options
Option | Alias | Description | Default |
|
| Path to the MCP configuration file | Auto-discovered |
| - | Use HTTP (Streamable HTTP) transport | stdio |
| - | HTTP mode listening port | 8080 |
|
| Workspace folder for | Current directory |
| - | Output verbose diagnostic logs to stderr | Off |
暴露的 3 个 Tool
Tool | 说明 |
| 列出所有上游 MCP server 的可用能力(tools/prompts/resources),可选 |
| 查询某个能力的完整调用方式(参数 schema 等),输入限定名 |
| 实际调用某个能力,传入限定名 + arguments |
配置文件格式
兼容 VS Code 族(servers 键)和 Claude/Cursor 族(mcpServers 键),自动推断 transport 类型:
{
"servers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"],
"env": { "API_KEY": "..." }
},
"remote-server": {
"type": "http",
"url": "https://example.com/mcp",
"headers": { "Authorization": "Bearer xxx" }
}
}
}支持变量替换:
${workspaceFolder}— 工作区目录${env:VAR_NAME}— 环境变量
配置文件发现顺序(未指定 --config 时):
--config显式指定当前目录
mcp.json当前目录
.mcp.json.vscode/mcp.jsonclaude_desktop_config.json
架构
AI 工具 ←stdio/http→ McpHub ←stdio/http→ 多个上游 MCP Server
│
├── list_mcp_capabilities → 聚合所有 server 的 tools/prompts/resources
├── describe_mcp_capability → 透传 schema 详情
└── call_mcp_capability → 透传调用详见 设计文档。
This server cannot be deployed
Maintenance
Related MCP Connectors
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs5 npm1MIT
- AlicenseAqualityBmaintenanceEnables LLMs to inspect and test other MCP servers by listing and calling their tools, reading resources, and getting prompts. Supports stdio, SSE, and HTTP transports for both local and remote MCP server inspection.79 npm1MIT
- AlicenseAqualityDmaintenanceAggregates tools from multiple MCP servers, acting as a proxy to provide unified access to various AI agents and tools.104 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access a unified catalog of tools from various APIs (OpenAPI, GraphQL, MCP, Google Discovery) through the MCP protocol.MIT