7 MCP servers eat 67,300 tokens (33.7% of a 200k window) before your first message - we measured it. MCP Shrink is a hosted compression proxy for any remote MCP server: tool definitions become ~54-token stubs that lazy-load on call, tool responses are distilled before they hit your context, and a dashboard shows tokens saved live. Works with any MCP client (Claude Desktop, Code, Cursor, Cline). Existing compressors are all local stdio proxies - nobody offers hosted. Validating demand before

Why we're building this: while auditing MCP setups we kept seeing the same thing - Claude Code burning 67k tokens on tool definitions from just 7 servers before the first message. The open-source compressors (mcpx, slim-mcp, mcp-diet and friends) all solve it locally as stdio proxies: clone, configure, run Node, re-point every client, on every machine. We want to plug ONE URL instead. MCP Shrink will compress tool definitions to ~54-token stubs, distill tool responses before they hit your context, and show live savings per server - but only if enough people want it. That's why this is a waitlist, not a landing page for a finished product: join, tell us your setup, and we build when demand is real. What's your MCP setup costing you in tokens?

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

MCP Shrink

Cut MCP context waste by ~90% - hosted compression proxy

Cut MCP context waste by ~90% - hosted compression proxy

Forum Threads

What does your MCP setup cost you in tokens today?

Forum Threads

What does your MCP setup cost you in tokens today?