TokenTally by Harlo MCP server
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.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the TokenTally by Harlo MCP server can do
The TokenTally by Harlo MCP server is published by tokentally.mike-tusa.workers.dev, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (1 tool: truncate_to_budget) and create or change data (2 tools: chunk_text and estimate_cost). 1 tool only reads.
1 tool reads private data (count_tokens).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 0.1.0.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.
- Warn
The server marks "truncate_to_budget" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.
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.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 2, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tokentally.mike-tusa.workers.dev/mcp: tools/list returned 4 tools to an anonymous client, including truncate_to_budget (destructive), chunk_text (write), estimate_cost (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "truncate_to_budget" read-only (readOnlyHint: true), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.
The server marks "truncate_to_budget" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "truncate_to_budget" says "truncate": a word for removing or ending something.
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.
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/mcpclaude mcp add --transport http tokentally https://tokentally.mike-tusa.workers.dev/mcpRun 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.
{
"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://radar.anlyon.com/api/v1/servers/dev.workers.mike-tusa.tokentally/tokentally/verify?hash=ba45c34d9a9255a040b20bfee4cd6b2617c7b29796c2918ec5c58fb0a2713594" | jq -e '.changed == false'Pinned hash ba45c34d9a92, from Nov 14, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.mike-tusa.tokentally/tokentally/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.mike-tusa.tokentally/tokentally)Source: MCP Registry. Synced Nov 1, 2026, 17:17 UTC.
TokenTally by Harlo MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TokenTally by Harlo MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TokenTally by Harlo MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: truncate_to_budget.
Can the TokenTally by Harlo MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the TokenTally by Harlo MCP server have?
- 4 tools: 1 destructive, 2 write, 1 read. truncate_to_budget, chunk_text, estimate_cost and count_tokens.
Does the TokenTally by Harlo MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TokenTally by Harlo MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the TokenTally by Harlo MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.