OpenRouter measures how MCP, CLI, and skills cost agent context tokens
AIOpenRouter measured input tokens for one GitHub task across a CLI, a skill, and the GitHub MCP server on several models. The default 46-tool MCP server used 59,417 input tokens on Claude Sonnet 5.5, against 1,421 for the gh CLI. The post shows how to count tool-definition tokens and how its Tool Search server tool reduces up-front cost, with results that vary by model.
AIWhy it matters.
The post measures what MCP servers, CLIs, and skills each add to context and shows how Tool Search and result scoping change the token cost.
Source details
OpenRouter Blog · openrouter.aiPublished · added here
Original title: MCP vs CLI vs Skills: What Each Costs in Context