Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.
Connect Remote server
claude mcp add --transport http tokentally https://tokentally.mike-tusa.workers.dev/mcp --header "Authorization: Bearer <YOUR_API_KEY>"
{
"mcpServers": {
"tokentally": {
"url": "https://tokentally.mike-tusa.workers.dev/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
{
"servers": {
"tokentally": {
"type": "http",
"url": "https://tokentally.mike-tusa.workers.dev/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
Settings > Connectors > Add custom connector
URL: https://tokentally.mike-tusa.workers.dev/mcp
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools 4 found in our last check
count_tokensCount tokens for text in o200k_base and cl100k_base side by side, plus approximate Claude/Gemini/Llama counts with method notes. OpenAI counts (o200k_base, cl100k_base) are exact for those tokenizers. Claude, Gemini and Llama counts are APPROXIMATE (proxy encoding; real tokenize…
truncate_to_budgetTruncate text to max_tokens (keep start or end) for an encoding or model.
chunk_textSplit text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.
estimate_costEstimate USD cost per model from text or input_tokens plus output_tokens using a dated price table (prices_as_of 2026-10-27). Estimates, not live billing.
Headers
| Name | Description |
|---|---|
AuthorizationOptional, secret | Optional. 'Bearer <key>' for higher limits. Works without a key. |
Details
| Endpoint | https://tokentally.mike-tusa.workers.dev/mcp (Streamable HTTP) |
| First published | 1 Nov 2026 |
| Last updated | 1 Nov 2026 |
| Registry name | dev.workers.mike-tusa.tokentally/tokentally |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
