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

$MSFT

BEARISH2026-10-08

Price around the call

↓ 2026-10-08

By horizonMaturing · ~8 trading days to go

✗ +1.2%

✗ +0.8%

21d

…

Original post

Jim Liu · 2026-10-08

Seems that the OpenAI revenue miss is heavily weighted by the accounting that OpenAI Inference sold through $MSFT Azure only counts for 20% of sold value as revenue while Anthropic Inference sold through AWS counts for 100% of sold value as revenue. This is because MSFT has IP rights on OpenAI. On the flip side the 20% that OpenAI gets from MSFT is pure gross margin ex training cost while Anthropic Inference revenue via AWS needs to subtract off compute cost to get gross margin. Azure is probably the biggest server of OpenAI inference so how it’s accounted matters greatly.

View on X ↗