I added MCP servers to Claude Code. Here's what they cost in tokens.

Everyone talks about MCP servers as a way to extend Claude Code. Fewer people talk about what they cost.

Every MCP tool you register injects a tool-definition block into your context window on every single turn. That's not a one-time cost — it compounds across your entire session. I wanted to know the actual numbers, so I measured them.

What MCP tool definitions actually look like in your context

When Claude Code loads an MCP server, it reads the server's tool manifest and injects something like this into the system prompt:

<tool>

  name: read_file

  description: Read the contents of a file at the given path...

  inputSchema: { type: object, properties: { path: { type: string } }, required: ["path"] }

</tool>

That's roughly 80–150 tokens per tool, depending on how verbose the description and schema are. A server with 10 tools = 800–1,500 tokens added to every turn of your session.

I measured three real MCP server configurations

I ran sessions with three different MCP server setups and tracked the token breakdown using (CLI) and tokenscope-mcp (MCP server). Both read Claude Code's native .jsonl logs — no proxy, no API key, no modified client.