McpHub MCP server
Aggregates multiple MCP servers into a unified set of tools for AI clients to list, describe, and call capabilities.
Also known as john0king/McpHub
- Stars
- 2
- Tools
- 3
- Downloads, 30 days
- —
- Latest version
- 0.0.1.1
- Last commit
- Aug 10, 2026
- License
- MIT
What is McpHub MCP?
McpHub aggregates multiple MCP servers into a unified set of tools for AI clients to list, describe, and call capabilities. It exposes 3 tools, such as list_mcp_capabilities, describe_mcp_capability, call_mcp_capability.
Summary generated from the project's README
About McpHub MCP server
McpHub acts as a bridge that aggregates the tools, prompts, and resources from various MCP servers into a single interface. Instead of connecting an AI client to many individual servers, you connect to this hub which exposes four fixed tools to manage all upstream capabilities. This setup simplifies how AI clients interact with complex environments containing multiple specialized servers.
Developers can run this server using stdio mode as the default or via HTTP mode on a specific port like 8080. The configuration supports both VS Code and Claude style formats, allowing you to define local commands or remote HTTP connections. It includes features like variable substitution for workspace directories and environment variables to make configuration more flexible across different machines.
What you can do with it
- 1Inventory all available capabilitiesAsk the AI to find every tool, prompt, and resource available across all connected MCP servers.
- 2Inspect specific tool schemasRequest the exact parameter requirements and schema for a specific capability using its qualified name.
- 3Execute remote or local toolsInstruct the AI to run a specific function from an upstream server by passing the necessary arguments.
Written from the project's README. Every use case is checked against a quote from it.
McpHub MCP tools 3
Detected from the READMElist_mcp_capabilitiesdescribe_mcp_capabilitycall_mcp_capability
Configuration
API_KEY
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablejohn0king/mcphub is public and reachablegithub.com/john0king/mcphub ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-10github.com/john0king/mcphub ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model3 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubMcpHub
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.json
Configure 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.json
Client connects to http://localhost:8080/ (Streamable HTTP).
CLI Options
| Option | Alias | Description | Default |
|---|---|---|---|
--config |
-c |
Path to the MCP configuration file | Auto-discovered |
--http |
- | Use HTTP (Streamable HTTP) transport | stdio |
--port |
- | HTTP mode listening port | 8080 |
--workspace |
-w |
Workspace folder for ${workspaceFolder} substitution |
Current directory |
--verbose |
- | Output verbose diagnostic logs to stderr | Off |
暴露的 3 个 Tool
| Tool | 说明 |
|---|---|
list_mcp_capabilities |
列出所有上游 MCP server 的可用能力(tools/prompts/resources),可选 kind 过滤 |
describe_mcp_capability |
查询某个能力的完整调用方式(参数 schema 等),输入限定名 serverName.capabilityName |
call_mcp_capability |
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。
McpHub MCP questions
What tools does McpHub MCP provide?
It exposes 3 tools, including list_mcp_capabilities, describe_mcp_capability, call_mcp_capability.
What tools does McpHub expose to AI clients?
It exposes three primary tools: list_mcp_capabilities, describe_mcp_capability, and call_mcp_capability.
How can I connect to McpHub via HTTP?
You can run McpHub in HTTP mode using the --http flag, and clients can connect to the listening port (default 8080) via Streamable HTTP.
Does McpHub support environment variables in its configuration?
Yes, the configuration format supports variable substitution for workspace directories and environment variables.