mcpField
A
ARCHON-MCP-CLIENT

ARCHON-MCP-CLIENT

github.com/herhuFrameworks & SDKs1Updated 28w ago

About ARCHON-MCP-CLIENT

ARCHON-MCP-CLIENT is a bridge for routing Claude Desktop stdio requests to the Archon Specs remote SSE backend over HTTPS. It is configured through Claude Desktop and run with npx.

Key features

  1. 01Proxy stdio requests to a remote SSE backend
  2. 02Connect to Archon Specs over HTTPS
  3. 03Keep stdout free of non-protocol logs
  4. 04Configure through Claude Desktop

Use cases

  1. 01Route Claude Desktop requests to Archon Specs
  2. 02Use a remote SSE backend from a stdio client

MCP support

Acts as an MCP client bridge, translating Claude Desktop stdio requests for the Archon Specs remote SSE backend. The README highlights JSON-RPC output hygiene for Claude Desktop.

Details

From the project README

archon-mcp-client

🚀 Live: https://archonspecs.dev

A completely silent, standards-compliant Model Context Protocol (MCP) client bridge that natively proxies Claude Desktop stdio requests directly into an Archon Specs SSE remote backend over HTTPS.

Unlike other public MCP proxies, this package guarantees complete stdout JSON-RPC hygiene, preventing log pollution that crashes Claude Desktop's strict parsers.

Usage

You do not need to install this library. Just configure your claude_desktop_config.json to execute it remotely via npx. Find more information and full documentation at https://archonspecs.dev/docs.html.

{
  "mcpServers": {
    "archon-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "archon-mcp-client",
        "https://archonspecs.dev/mcp/sse?apiKey=your_api_key_here"
      ]
    }
  }
}

Archon Specs — AI Backend Architecture Compiler

🌐 Website: https://archonspecs.dev
📚 Docs: https://archonspecs.dev/docs.html
📦 Library: https://archonspecs.dev/library.html

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.