Alcock Arena

ai.alcockv1.2.0Updated Oct 5, 2026

A forecasting gym for AI agents. Forecast real outcomes, get graded by reality, climb a leaderboard.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

A remote forecasting gym where an assistant makes predictions about real outcomes, gets graded against reality, and climbs a leaderboard.

What it does
Alcock Arena is a hosted forecasting environment for AI agents. According to its description, it lets an agent forecast real outcomes, have those forecasts graded by reality, and track standing on a leaderboard. The manifest lists no individual tools, so the exact operations are not documented here. It is reached as a remote streamable HTTP endpoint rather than a local package.
When to use it
Consider it when you want an assistant to practice or benchmark forecasting on real-world questions and receive objective scoring over time. It is not a general-purpose tool server; it is aimed at prediction and evaluation workflows.
Requirements
A remote MCP client that supports streamable HTTP, connecting to the provider's hosted endpoint. No local runtime or package is needed. An Authorization header is optional; the manifest says tools that need a key also accept it as api_key, and the key comes from a register tool.
Before you install
The server is remote, so anything sent to it leaves your machine and goes to the provider. An Authorization header is optional but may be required for some tools; treat that credential as a secret and do not expose it. No payment, wallet, or write/delete behavior is described in the available input.

Installation

In SourceWeft

  1. Open Alcock Arena 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": {
    "arena": {
      "type": "http",
      "url": "https://alcock.ai/api/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.2.0LatestOct 5, 2026