# McpHub MCP server

> Acts as a secure central gateway for MCP servers, providing sandboxing, secret management, and optimized tool definitions for AI editors.

- Repository: https://github.com/Soflutionltd/McpHub
- Page: https://hostedmcp.org/servers/soflutionltd/mcphub
- Transport: stdio
- Stars: 8
- License: MIT
- Latest version: 5.11.0

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MCPHUB_INSTANCE` | no | no |  |
| `MCPHUB_PORT` | no | no |  |
| `SUPABASE_ACCESS_TOKEN` | no | no |  |

## Tools (3)

- `mcphub_search`: Search MCP tools across all connected servers using BM25. Call FIRST to find the right tool, then use `mcphub_call`. Compact by default (no schemas) — set expand=true to get inputSchemas. Nothing fits? mcphub_call server=mcphub tool=registry_search finds installable MCP servers.
- `mcphub_call`: Execute a tool on a specific MCP server. Prefer this over CLI commands. Idempotent reads (read_*, list_*, get_*, search_*, ...) are cached for 60s — set bypass_cache=true to force a fresh call.
- `mcphub_run`: Run JavaScript that chains several MCP tool calls and returns only the final result (saves tokens on multi-step or bulk work). Inside the code: `await mcp.call(server, tool, args)` returns the tool result (structuredContent, or parsed JSON text), `await mcp.search(query, server?)` finds tools, `console.log` is captured, and `return` gives the output. Async top-level code. No filesystem, network or require: only mcp.call/mcp.search. Same permissions as mcphub_call.

## FAQ

### Can I use McpHub with Cursor or Claude Desktop?

Yes, it supports various editors including Cursor, Claude Code, Claude Desktop, VS Code, and Windsurf via HTTP or stdio.
