Connect your AI client via MCP

Endpoint (paste into an MCP client — anonymous, free, no key)

https://mcp.koalcheck.com/mcp

Or copy this and send it to your AI to set it up:

Add the "koalcheck" MCP server to my client and connect. It is a remote Streamable-HTTP server at https://mcp.koalcheck.com/mcp — connect anonymously, no API key or login needed (the free tools work right away). If my client supports a remote/HTTP MCP server directly, just use that URL. If my client config only accepts a local command (e.g. Claude Desktop's mcpServers, which rejects a bare "url"), bridge it with command "npx" and args ["-y","mcp-remote","https://mcp.koalcheck.com/mcp"]. Then tell me to fully restart the client, and list the koalcheck tools you can call. It provides US-equity research tools built on an analyst track-record engine (who has actually been right, priced vs SPY, cross-checked with SEC & FINRA).

Capabilities User guide

← @jiahanjimliu

$META

BULLISH2026-09-28

Price around the call

↑ 2026-09-28

By horizonMaturing · ~1 trading days to go

✗ -1.6%

✗ -1.9%

21d

…

Original post

Jim Liu · 2026-09-28

$META AI Cloud Launched! As I have always said, there are many companies that are capable of AI Software Infrastructure. Meta is among the best and is vertically integrated with its own model. Meta will sell: 1. AI Tools 2. Muse Inference API 3. Business Agents for WhatsApp, Instagram, Messenger The impact will be higher demand for bare metal from Meta and a more competitive market for inference as Meta Muse has extremely competitive pricing to OpenSource models. Meta will be able to scale its AI software platform at negligible cost as long as it has access to bare metal. Scaling means Meta will be able to amortize its training cost for Muse over a larger base. Meta may not have enough compute but look for Meta to aggressively bid for Colocation, Bare Metal, Powered Land.

View on X ↗