mcpbeat Sign in

TokenTally by Harlo MCP Server

by workers-mike-tusa-tokentally Your server? Claim it
answering

TokenTally by Harlo is answering right now. Last checked 6 min ago. It exposes 4 tools.

Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.

Uptime history 22 hours of history
22 hours agonow
100.0%
Uptime 24h
82 of 82 checks
4
Tools
read from the server
120 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check TokenTally by Harlo every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

run in your terminal
claude mcp add tokentally --transport http https://tokentally.mike-tusa.workers.dev/mcp
Settings → Connectors → Add custom connector, then paste this address
https://tokentally.mike-tusa.workers.dev/mcp
~/.codex/config.toml
[mcp_servers.tokentally]
url = "https://tokentally.mike-tusa.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "tokentally": {
      "url": "https://tokentally.mike-tusa.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "tokentally": {
      "type": "http",
      "url": "https://tokentally.mike-tusa.workers.dev/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

chunk
chunk_text
Split text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.
count
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 tokenizers differ, often by 10-20%, and newer Claude tokenizers by ~30% or more). Cost estimates use a dated price table (prices_as_of 2026-10-27) and are estimates, not live billing. Stateless: text is not stored or logged; no URL fetching. Max input is 256 KB. A single unbroken run of characters near that cap may hit a CPU timeout (503); normal text at the cap is supported.
estimate
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.
truncate
truncate_to_budget
Truncate text to max_tokens (keep start or end) for an encoding or model.

Endpoints

URLTransportStateLatencyChecked
https://tokentally.mike-tusa.workers.dev/mcp streamable-http answering 80 ms 6 min ago

Alternatives to TokenTally by Harlo

same job, measured the same way
LLMKit
by olsols4

Token counting, RAG chunking, truncation, HTML to Markdown and JSON repair

answering
Agentsearch MCP
by isaiahdupree

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

3 tools answering
MCP File Processor
by opafex

Text extraction, keyword extraction, language detection, and chunking for RAG

287 installs/wk local only
MCP File Processor
by intelagentstudios

Text extraction, keyword extraction, language detection, and chunking for RAG

43 installs/wk local only
URL to Markdown Converter
by cleandata-labs

Web pages and PDFs to clean, LLM-ready Markdown with token counts, small crawls and RAG chunks.

answering
lintlab PDF To Markdown
by lintlab

Convert PDF URLs to clean Markdown and text for RAG and LLM input. Pay per PDF on Apify.

answering
Scrapiq
by scrapiq

Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.

1 tools answering
Web2MD
by kanavsingla28

Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).

49 installs/wk local only

TokenTally by Harlo — questions

Answers built from our own checks of this server.

What can TokenTally by Harlo do?
It exposes 4 tools, read directly from the server on our last check. Among them: chunk_text, count_tokens, estimate_cost, truncate_to_budget. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is TokenTally by Harlo working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 82 of 82 checks got a reply (100.0%), average response time 120 ms. The bar chart above shows every period we have measured.
How do I connect TokenTally by Harlo?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does TokenTally by Harlo need an API key?
No. TokenTally by Harlo completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is TokenTally by Harlo?
It answers our handshake in 120 ms on average, which is faster than 88% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.