Skip to content

Why OneTool Exists

MCP doesn't scale.

Here's the problem: every MCP server you add makes your AI dumber. Not in theory - in practice.

What's actually happening

Context rot is real

LLM performance degrades as input tokens pile up. Chroma's research measured this: the 10,000th token is handled less reliably than the 100th.

"Context must be treated as a finite resource with diminishing marginal returns." - Anthropic Engineering

MCP eats your context for breakfast

Every MCP server you connect adds thousands of tokens before you've said anything.

Setup Token Cost What that means
5 servers ~55K Gone before you type
10+ servers 100K+ Context nearly full
Tool calls N loops LLM deliberation tax

Each server makes context rot worse, not just bigger.

Vibe coding catches up with you

Collins Dictionary's 2025 Word of the Year: Andrej Karpathy's term for accepting code "that looks roughly right."

A UK study of 120 firms found 41% more debugging time at scale. Day 2 maintenance of AI-generated code is still an unsolved problem.

What OneTool does differently

One tool. Code execution. That's basically it.

The numbers

Metric Traditional MCP OneTool
Token usage 150,000 2,000
Cost per query $0.025 $0.002
Tool calls 5+ 1

98.7% fewer tokens. 10x cheaper. One call instead of five.

How it works

Traditional MCP:
  Load tools (55K) → Reason → Call tool → Reason → Return
  Total: ~150K tokens, 5+ reasoning loops

OneTool:
  run request → Execute Python → Return
  Total: ~2K tokens, 1 call

Instead of loading 50 tool schemas, LLMs write Python:

__ot brave.search(query="AI trends 2026")

The approach

LLMs write Python to call functions. No JSON schema parsing. No tool selection loops. You see exactly what's being called because you wrote it.

15 packs built-in. Adding your own is dropping a Python file in a folder.

MIT Technology Review calls this shift "from vibe coding to agentic engineering." Whatever you call it, the token math works out.

What you get

  • 24x fewer tokens, same accuracy
  • Drop a Python file, get a new pack
  • AST validation before execution
  • ot-bench for testing LLM + MCP combinations
  • Proxy mode wraps existing MCP servers