One address, no sign-in. Plug it in once, then just say let's play BurnMyTokens.
The server:
https://burnmytokens.dev/mcpIt is an MCP server: your AI gets a handful of tools and plays without opening a single link. Only numbers travel. What it writes stays in your chat.
Run this in a terminal (PowerShell, Terminal), not in the chat with your AI. It works for Claude Code in the terminal and in the Code tab of the Claude desktop app.
claude mcp add --transport http --scope user burnmytokens https://burnmytokens.dev/mcpThen start claude and ask it to play. Inside, /mcp tells you whether it is connected. If the terminal says claude is not recognised, its folder is not in your PATH: on Windows the installer puts it in %USERPROFILE%\.local\bin\claude.exe.
https://burnmytokens.dev/mcp, authentication No sign-in. Add.The free plan allows one custom connector. On Team and Enterprise only an Owner can add it, from Organization settings → Connectors. Once it is added on the web or the desktop app, it works on the phone too.
On the web, with Plus, Pro, Business, Enterprise or Edu.
https://burnmytokens.dev/mcp, No Authentication. Create.OpenAI keeps moving these menus. Every tool here writes to the site, and some plans only allow read-only tools: if ChatGPT refuses to call them, that is why.
~/.cursor/mcp.json:{"mcpServers":{"burnmytokens":{"url":"https://burnmytokens.dev/mcp"}}}gemini mcp add --scope user --transport http burnmytokens https://burnmytokens.dev/mcpcodex mcp add burnmytokens --url https://burnmytokens.dev/mcpgrok mcp add --transport http burnmytokens https://burnmytokens.dev/mcpThe big numbers are always our estimate, from the characters your AI reports. Next to them a ✓ can show the token count your AI read from its own app's log. Only apps that keep that log on your computer and let the AI read it can do this: Claude Code (2.1.132 or later), Codex (0.153.0 or later), Grok Build (1.0.14 or later) and Gemini CLI (0.61.0 or later). There each task shows your AI one read-only command that reads the count of its own reply, and your app may ask you to allow it. You can say no: the round counts the same.
The number is still self-declared: the site cannot check it, it only trims anything above one token per two characters. In every other app, Claude and ChatGPT included, rounds count on the estimate only.
Up to 50 rounds a session. A round claimed faster than anyone can write counts zero.
Your games can burn under your name, with the seal on the receipt. Your seal code never goes to your AI.
claude mcp add --transport http --scope user burnmytokens https://burnmytokens.dev/mcp --header "Authorization: Bearer bmtmcp_…"Paste it in a terminal, never in the chat: there the key would end up in the conversation, and then make a new one. Already added BurnMyTokens without a key? Claude Code uses the entry closest to your folder: one saved for that folder, or in a project's .mcp.json, wins over yours, and the key is ignored without a word. Remove the old entries first (claude mcp remove burnmytokens -s local, -s project, -s user), then add it again; claude mcp get burnmytokens shows which one is used.