TokenTally by Harlo
REMOTE · TOKENTALLY.MIKE-TUSA.WORKERS.DEV
Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.
Available components
Last scanned (56 minutes ago)
Scores higher than 44% of remote servers
Reachable. Last reached 5 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 607 tokens (~151/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 27% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "truncate_to_budget" implies "truncate" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 0
- Stability: unverified → 0.03 ▲ functional
- 1 Nov 26 61
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://tokentally.mike-tusa.workers.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mike-tusa.workers.dev | CN=WE1,O=Google Trust Services,C=US | 12 Oct 2026 | 10 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | f05aa95d8943eeed0e4e86dd1f6f1e02 |
| SANs: mike-tusa.workers.dev, *.mike-tusa.workers.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tokentally.mike-tusa.workers.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| workers.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tokentally.mike-tusa.workers.dev/mcp | Verified | 200 | |
| http (plaintext) | http://tokentally.mike-tusa.workers.dev/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
chunk_text Chunk text for RAG ~77
Split text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.
| Name | Type | Req | Description |
|---|---|---|---|
| chunk_tokens | integer | – | – |
| encoding | string | – | – |
| model | string | – | – |
| overlap_tokens | integer | – | – |
| text | string | yes | Text (≤256 KB). URLs are not fetched. |
No output schema declared.
No examples provided.
count_tokens Count tokens ~189
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.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Text (≤256 KB). URLs are not fetched. |
No output schema declared.
No examples provided.
estimate_cost Estimate LLM cost ~84
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.
| Name | Type | Req | Description |
|---|---|---|---|
| input_tokens | integer | – | – |
| models | array | – | – |
| output_tokens | integer | – | – |
| text | string | – | Text (≤256 KB). URLs are not fetched. |
No output schema declared.
No examples provided.
truncate_to_budget Truncate to token budget ~73
Truncate text to max_tokens (keep start or end) for an encoding or model.
| Name | Type | Req | Description |
|---|---|---|---|
| encoding | string | – | – |
| keep | string | – | – |
| max_tokens | integer | yes | – |
| model | string | – | – |
| text | string | yes | Text (≤256 KB). URLs are not fetched. |
No output schema declared.
No examples provided.
How do I install the TokenTally by Harlo MCP server?
TokenTally by Harlo is a hosted endpoint at https://tokentally.mike-tusa.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · tokentally.mike-tusa.workers.dev
claude mcp add --transport http dev-workers-mike-tusa-tokentally-tokentally 'https://tokentally.mike-tusa.workers.dev/mcp'
What is the TokenTally by Harlo MCP server?
TokenTally by Harlo is an MCP server listed in the public MCP registry as dev.workers.mike-tusa.tokentally/tokentally. Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost. This page covers its hosted endpoint (https://tokentally.mike-tusa.workers.dev/mcp).
Is the TokenTally by Harlo MCP server safe to use?
TokenTally by Harlo scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the TokenTally by Harlo MCP server expose?
TokenTally by Harlo exposes 4 tools: count_tokens, truncate_to_budget, chunk_text, estimate_cost. Their descriptions and schemas cost roughly 423 tokens of context every time the server is loaded.
Does the TokenTally by Harlo MCP server require authentication?
No. We connected to TokenTally by Harlo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the TokenTally by Harlo MCP server still maintained?
TokenTally by Harlo is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.