Skip to content
anlyon.devby Anlyon

TokenTally by Harlo

dev.workers.mike-tusa.tokentally/tokentallytokentally.mike-tusa.workers.devstreamable-httpv0.1.0Scanned

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

4 tools: 1 can delete or cancel things, 2 change things and 1 only read.

Tools: 1 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 0
  • 2 findings

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →
Compare with similar serversMarkdownJSONReport this listing

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

4 tools

Deletes or cancels 1Claude Code: deny
  • truncate_to_budgetTruncate text to max_tokens (keep start or end) for an encoding or model.2 findings

    Why it is in this group

    • The name "truncate_to_budget" says "truncate": a word for removing or ending something.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "truncate_to_budget" read-only (readOnlyHint: true), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.

      What this check looks for
    • Warn

      The server marks "truncate_to_budget" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    Truncate text to max_tokens (keep start or end) for an encoding or model.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 2Claude Code: ask
  • chunk_textSplit text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Split text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • 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).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • count_tokensCount tokens for text in o200k_base and cl100k_base side by side, plus approximate Claude/Gemini/Llama counts with method notes.Reads private dataNo findings

    Why it is in this group

    • The name "count_tokens" says "count": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "count" and "note": it reads notes.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • Warntruncate_to_budget

    The server marks "truncate_to_budget" read-only (readOnlyHint: true), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.

    What this check looks for
  • Warntruncate_to_budget

    The server marks "truncate_to_budget" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http tokentally https://tokentally.mike-tusa.workers.dev/mcp
claude mcp add --transport http tokentally https://tokentally.mike-tusa.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__tokentally__count_tokens"
    ],
    "ask": [
      "mcp__tokentally__chunk_text",
      "mcp__tokentally__estimate_cost"
    ],
    "deny": [
      "mcp__tokentally__truncate_to_budget"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as tokentally. Review it before you use it.

Capability tags behind 1 rule
  • mcp__tokentally__count_tokens private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/dev.workers.mike-tusa.tokentally/tokentally/verify?hash=ba45c34d9a9255a040b20bfee4cd6b2617c7b29796c2918ec5c58fb0a2713594" | jq -e '.changed == false'

Pinned hash ba45c34d9a92, from Nov 1, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/dev.workers.mike-tusa.tokentally/tokentally/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

anlyon.dev badge for dev.workers.mike-tusa.tokentally/tokentally
[![anlyon.dev](https://anlyon.dev/badge/dev.workers.mike-tusa.tokentally/tokentally.svg)](https://anlyon.dev/servers/dev.workers.mike-tusa.tokentally/tokentally)

Source: MCP Registry. Synced Nov 1, 2026, 17:17 UTC.