TopxAI Models

com.topxea.aiv1.0.0Updated Oct 6, 2026

Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

Lets an assistant query several third-party large language models, including Claude, GPT, Grok, GLM, Kimi and DeepSeek, from one client.

What it does
This remote MCP server exposes access to multiple large language models through a single endpoint, so an assistant can send prompts to Claude, GPT, Grok, GLM, Kimi or DeepSeek from the same client. The registry description states that usage is charged as token price plus a $0.001 call fee. No individual tool names or parameters are listed in the supplied material.
When to use it
Use it when you want one assistant session to reach several different model providers without configuring each provider separately, or when you want to compare or route requests across those models. It is less useful if you already have direct access to the models you need or want to avoid per-call charges.
Requirements
A remote MCP endpoint at over streamable HTTP; no local package or runtime is declared. A TopxAI account and API key are needed, supplied as the required secret header Authorization in the form Bearer followed by the key. Network access to the endpoint is required.
Before you install
A secret header named Authorization is required, carrying a Bearer token that is your TopxAI API key; treat it as a credential and avoid exposing it in shared or logged configurations. Calls are billed: the description mentions token price plus a $0.001 call fee, so usage costs money. Prompts and any content sent to the models leave your machine and go to the provider.

Installation

In SourceWeft

  1. Open TopxAI Models in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "models": {
      "type": "http",
      "url": "https://ai.topxea.com/mcp/models"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 6, 2026