MCPHub
Unified hub for centrally managing and dynamically orchestrating multiple MCP servers. 2,065 GitHub stars and 41 commits on main in the last 30 days.
“Unified hub for centrally managing and dynamically orchestrating multiple MCP servers. 2,065 stars and 41 commits on main in the last 30 days.”
INSTALL THIS SERVER
{
"mcpServers": {
"mcphub": {
"command": "npx",
"args": [
"-y",
"mcphub",
"serve"
]
}
}
}
{
"mcpServers": {
"mcphub": {
"command": "npx",
"args": [
"-y",
"mcphub",
"serve"
]
}
}
}
{
"mcpServers": {
"mcphub": {
"command": "npx",
"args": [
"-y",
"mcphub",
"serve"
]
}
}
}
{
"mcpServers": {
"mcphub": {
"command": "npx",
"args": [
"-y",
"mcphub",
"serve"
]
}
}
}
{
"mcpServers": {
"mcphub": {
"command": "npx",
"args": [
"-y",
"mcphub",
"serve"
]
}
}
}
5 TOOLS AVAILABLE
OUR ASSESSMENT
- 2,065 GitHub stars.
- 41 commits on main in the last 30 days.
- Apache-2.0 license.
- Single-binary deployment; minimal configuration.
- Active community development.
- Lighter on enterprise features (audit logging, policy) compared with ToolHive.
- Community-maintained; no commercial support tier.
- orchestrate_call delegates to underlying MCP servers; latency adds with each hop.
Optional token authentication for multi-tenant deployments. orchestrate_call inherits permissions of the registered downstream servers; ensure each registered server uses appropriately scoped credentials.
Indie developers managing many MCPs without enterprise overhead; teams that want orchestration without a full gateway stack; learning environments where MCPHub gives a clear lifecycle view.
TECHNICAL DETAILS
ADOPTION METRICS
// Reading this2,065 stars on samanhappy/mcphub. 41 commits on main in the last 30 days.
// Reading thisPairs with ToolHive, Agent Gateway, Docker MCP Gateway, MCP Registry, ACI for MCP orchestration. MCPHub owns the indie/learning slot.
SOURCES & VERIFICATION
We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.
The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.
| Source | Their rating | Their star count | Their downloads | Last synced |
|---|---|---|---|---|
| AutomationSwitch This page | 4.5editorial | 2,065 | — | MAY 9, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 9, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 9, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 9, 2026 |
| Smithery | — unrated | unavailable | unavailable | MAY 9, 2026 |
// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.
OTHER DEV TOOLS MCP SERVERS
GitHub
Official GitHub MCP server. 29,469 stars, MIT, 33 commits on main in the last 30 days. Repo, issue, PR, action, and code search tools backed by the GitHub REST + GraphQL APIs.
Playwright
Official Microsoft Playwright MCP server. Browser automation tools (navigate, click, fill, screenshot, evaluate JS, network capture) backed by Playwright. 31,942 stars, 35 commits/30d, Apache-2.0.
FastMCP (Python)
The fast, Pythonic way to build MCP servers and clients. Maintained by PrefectHQ. 25,133 GitHub stars and 92 commits on main in the last 30 days. The dominant Python MCP framework.
Repomix
Pack the entire repository into a single AI-friendly file. Optimised context for feeding codebases to Claude, ChatGPT, Gemini, and others. 24,515 GitHub stars and 100 commits on main in the last 30 days.
Serena
Powerful MCP toolkit for coding. Provides semantic retrieval and editing capabilities, positioned as the IDE for the agent. 23,971 GitHub stars and 100 commits on main in the last 30 days.
MCP Python SDK
The official Python SDK for Model Context Protocol servers and clients. Maintained by the Model Context Protocol project. 22,984 GitHub stars and 5 commits on main in the last 30 days.
DISCUSS YOUR
MCP REQUIREMENTS.
Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.