What does your MCP setup cost you in tokens today?

We measured ours: 7 servers = 67,300 tokens before the first message - a third of a 200k window, gone. That's the problem MCP Shrink attacks: a hosted URL that compresses tool definitions to ~54-token stubs and distills tool responses before they hit your context.

We are validating demand before writing the production code (the waitlist decides if this gets built): updatesbyai.com/waitlist

Curious about two things:1. How many MCP servers do you run, and how many tools do they expose?2. Have you tried the local compressors (mcpx, slim-mcp, mcp-diet)? What pushed you away or kept you?