TokenTally by Harlo
by tokentally.mike-tusa.workers.dev in Onchain & crypto
Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.
https://tokentally.mike-tusa.workers.dev/mcp- Tools
- 4
- open to any client
- Uptime
- 100%
- last 30 days
- Response time
- 120 ms
- 150 ms slowest 5%
- Last check
- Passed
- 2 h ago, next in 4 h
Reliability
Status and outage history · Atom feed · Watch with other listings
How to connect
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"tokentally-by-harlo": {
"type": "http",
"url": "https://tokentally.mike-tusa.workers.dev/mcp"
}
}
}4 tools
- count_tokens
Count 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…
- truncate_to_budget
Truncate text to max_tokens (keep start or end) for an encoding or model.
- chunk_text
Split text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.
- estimate_cost
Estimate 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.
Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 2 h ago | Passed | 200 | 120 ms |
| 13 h ago | Passed | 200 | 150 ms |