How does mcp-remote-server load its capabilities?
It fetches a JSON configuration from the URL specified in the `MCP_CONTROL_PLANE_URL` environment variable. The configuration lists tools, resources, and prompts, each with a remote handler endpoint.
@sirmews
Basic information
A declarative, composable model context protocol server that uses a remote config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-remote-server": {
"command": "bun",
"args": [
"run",
"index.ts"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A configurable Model Context Protocol (MCP) server that dynamically loads its capabilities from a remote configuration. It acts as a bridge between MCP clients and remote APIs by parsing a hosted JSON configuration defining tools, resources, and prompts.
Install with bun install, set the MCP_CONTROL_PLANE_URL environment variable to your configuration endpoint, then run bun run index.ts.
—
It fetches a JSON configuration from the URL specified in the `MCP_CONTROL_PLANE_URL` environment variable. The configuration lists tools, resources, and prompts, each with a remote handler endpoint.
Tool handlers must return JSON that the server wraps in an MCP tool response. Resource handlers must return content matching the specified mimeType. Prompt handlers can return either a string (wrapped in a message) or an array of MCP-formatted messages.
Only HTTP/HTTPS handler endpoints are supported. The configuration must be accessible via HTTP GET. Handler responses must be JSON-compatible. The server runs locally only (standard MCP limitation).
The configuration is automatically refreshed every 60 seconds.
It requires Bun (v1.1.32 or later) as the JavaScript runtime.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
不止于 CSS

Model Context Protocol Servers
Comments