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

$IREN

BULLISH2026-05-27

Price around the call

↑ 2026-05-27

By horizon✗ miss-26.8%

✗ -1.0%

✗ -3.7%

21d

✗ -26.8%

Original post

Jim Liu · 2026-05-27

Anthropic CFO Krishna Rao Interview: How They Plan Compute https://t.co/nvRA1OM5DU 1. They buy Nvidia GPUs, Google TPUs, Amazon Trainium and use all 3 fungibly. 2. Built in-house orchestration to utilize each generation of different chip most efficiently. 3. Works as close to the bare metal on all 3 chips as possible to have maximum flexiblity and efficiency. 4. Has influence over Amazon Trainium design roadmap. Sometimes works directly with Annapurna engineers. 5. They have allocation for their own engineers separate from research which in itself has an allocation. 6. Model Development has highest priority even over Customer allocation. 7. ROI of being on the best frontier model is very high, especially enterprise. Immediately when Opus 4.7 comes out, almost everyone switches to

View on X ↗