mcpd
Verified Safeby xandwr
Overview
Aggregates multiple Model Context Protocol (MCP) servers into a single endpoint for clients, allowing centralized management and on-demand spawning of tools.
Installation
mcpd serveSecurity Notes
The daemon's core function involves spawning and running arbitrary user-defined commands (`mcpd register <name> <command> [args...]`) with custom environment variables. This is a powerful feature that, if misused or if the user's system is compromised, could allow arbitrary code execution. `mcpd` itself does not introduce network attack surfaces, as it operates over stdio, but it acts as an executor for local commands. It is safe to run provided the user explicitly trusts all commands and environment variables they register with it.
Similar Servers
mcp-context-forge
A comprehensive Model Context Protocol (MCP) gateway and proxy that unifies REST, MCP, and A2A services, providing features like federation, virtual servers, rate-limiting, security, and an optional admin UI for managing web content and file conversions to markdown.
mcphub
A hub for managing, orchestrating, and providing a unified API for various Model Context Protocol (MCP) servers and their tools, including user management, OAuth services, and discovery of external servers.
mcpm.sh
This server provides a command-line interface to manage Model Context Protocol (MCP) servers, allowing users to discover, install, configure, run, share, and monitor them.
aicode-toolkit
Acts as an MCP proxy server to connect AI agents to multiple underlying MCP servers through a single connection, enabling progressive tool discovery and reducing initial token usage for tool descriptions.