Urgent.News

What's breaking now, across thousands of outlets.

AI

I Benchmarked 10 MCP Servers — One of Them Burns 47K Tokens Just to Say Hello

I Benchmarked 10 MCP Servers — One of Them Burns 47K Tokens Just to Say Hello 10 popular MCP servers. 847 tools total. 312K tokens of JSON schemas. One server alone wastes more tokens than a full GPT-3 conversation. Here are the results. What I did I installed the 10 most popular MCP servers from the official registry. Connected each one to a token counter. Measured exactly how many tokens get…

Testing 10 popular MCP servers revealed one server consumed 47,293 tokens just to list files in a user's Google Drive. After benchmarking, it became clear that MCP servers impose significant token overhead before any user queries. The main drivers of this overhead were JSON schema definitions, with 42% of tokens used for inputSchema properties and type definitions.

Google Drive's MCP server had the most tools, each with deep nested schemas. The token cost for connecting 10 servers at $3 per million input tokens would amount to $0.34 - even exceeding the cost of a Claude Pro subscription. By building mcptoon, a CLI proxy that caches schemas and strips result wrapping, users can reduce token usage by up to 97%, saving significant costs per conversation.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Claude Code Is Burning Your Token Budget. Here's the Receipt.

Claude Code Is Burning Your Token Budget. Here's the Receipt. I found $2,500/year of hidden token waste in my Claude Code setup. It was the MCP servers.

  • Claude Code using significant token budget, potentially $2,500/year
  • Multiple MCP servers in setup inject schema into every conversation
  • Three-step process to reduce waste: audit servers, remove unused, proxy remaining with mcptoon

MCP Was a Mistake. Here Are 200,000 Tokens That Prove It.

MCP Was a Mistake. Here Are 200,000 Tokens That Prove It. "mcp were a mistake. bash is better." — Peter Steinberger, OpenClaw founder I didn't want to believe it either.

  • MCP protocol touted as AI's USB-C but costly mistake
  • 111,713 tokens injected into context window before interaction
  • 98.7% reduction in token consumption possible with runtime schema loading

More from Sunday 23 August →