Skip to content

Model Ruler — AI Cost Calculators MCP server

io.github.helphub369/model-rulerhelphub369streamable-httpv1.0.4Scanned

Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.

12 tools: 12 change things.

Tools: 0 delete, 0 irreversible, 12 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

12 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Model Ruler — AI Cost Calculators MCP server can do

The Model Ruler — AI Cost Calculators MCP server is published by the GitHub account helphub369. It has 12 tools. It can create or change data (12 tools: token-counter, provider-cost-calculator, self-host-breakeven-calculator, context-window-planner and 8 more), but cannot delete data. None of its tools only reads.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.0.4.

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.

12 tools

Changes things 12Claude Code: ask
  • agent-loop-cost-calculatorUse for LLM inference/reasoning cost per successful multi-step agent task, including failure overhead and context growth across turns.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
    Use for LLM inference/reasoning cost per successful multi-step agent task, including failure overhead and context growth across turns. Use agent-workflow-cost-calculator for iPaaS/app-action/MCP orchestration fees. Use automation-cost-calculator for generic Zapier/Make/n8n workflow billing.

    Annotations the server declares

    • title: Agent LLM Loop Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • agent-workflow-cost-calculatorUse for automation-platform/iPaaS cost of an AI agent workflow, including app-action fan-out and MCP tool-call accounting, explicitly excluding LLM token spend.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
    Use for automation-platform/iPaaS cost of an AI agent workflow, including app-action fan-out and MCP tool-call accounting, explicitly excluding LLM token spend. Use automation-cost-calculator for generic non-agent workflow billing. Use agent-loop-cost-calculator for LLM inference/reasoning cost per successful multi-step agent task.

    Annotations the server declares

    • title: Agent Workflow Platform Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • automation-cost-calculatorUse for generic or non-agent recurring workflow platform billing across Zapier task billing, Make credit billing, and n8n execution billing.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
    Use for generic or non-agent recurring workflow platform billing across Zapier task billing, Make credit billing, and n8n execution billing. Use agent-workflow-cost-calculator instead when the workflow is explicitly an AI agent with app actions or MCP tool calls. Use agent-loop-cost-calculator instead when the question is about LLM inference/reasoning cost per successful agent task.

    Annotations the server declares

    • title: Workflow Automation Platform Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • context-window-plannerUse when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).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
    Use when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).

    Annotations the server declares

    • title: Context Window Planner
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • eval-cost-calculatorUse when a user needs to budget an LLM evaluation run.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
    Use when a user needs to budget an LLM evaluation run. Given samples/models/trials, returns total cost, per-run cost, and parallel time estimate.

    Annotations the server declares

    • title: Evaluation Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fine-tune-roi-calculatorUse when a user is considering fine-tuning vs prompt engineering.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
    Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.

    Annotations the server declares

    • title: Fine-Tune ROI Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • observability-cost-calculatorUse when a user needs to budget LLM observability tooling.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
    Use when a user needs to budget LLM observability tooling. Returns monthly cost at given request volume with retention adjustment.

    Annotations the server declares

    • title: LLM Observability Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • provider-cost-calculatorUse when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers.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
    Use when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers. Given tokens per call and call volume, returns monthly cost plus a tier comparison table.

    Annotations the server declares

    • title: LLM Provider Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • quantization-calculatorUse when a user is planning to quantize an LLM to fit on smaller hardware.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
    Use when a user is planning to quantize an LLM to fit on smaller hardware. Given parameter count and precision transition, returns VRAM requirement, speedup estimate, and approximate quality delta.

    Annotations the server declares

    • title: Quantization Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rag-pipeline-cost-calculatorUse when a user needs end-to-end RAG cost estimation (embedding + vector store + generation).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
    Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation). Returns monthly cost with breakdown and dominant-component identification.

    Annotations the server declares

    • title: RAG Pipeline Cost Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • self-host-breakeven-calculatorUse when a user is deciding between API usage and self-hosted GPU inference at a given volume.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
    Use when a user is deciding between API usage and self-hosted GPU inference at a given volume. Returns breakeven token volume, monthly cost comparison, and go/no-go recommendation.

    Annotations the server declares

    • title: Self-Host Breakeven Calculator
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • token-counterUse when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload.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
    Use when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload. Given text and tokenizer family, returns low/high token range and byte-level measurements.

    Annotations the server declares

    • title: Token Counter
    • 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 private-data or untrusted-input or outbound.

Reads private data0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:05 UTC, unchanged since Oct 22, 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
12
Protocol version
2024-11-05
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 12 tools that change things (12 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry: tools/list returned 12 tools to an anonymous client, including token-counter (write), provider-cost-calculator (write), self-host-breakeven-calculator (write), context-window-planner (write), quantization-calculator (write) and 7 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

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 1.0.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http model-ruler https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry
claude mcp add --transport http model-ruler https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry

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": [],
    "ask": [
      "mcp__model-ruler__token-counter",
      "mcp__model-ruler__provider-cost-calculator",
      "mcp__model-ruler__self-host-breakeven-calculator",
      "mcp__model-ruler__context-window-planner",
      "mcp__model-ruler__quantization-calculator",
      "mcp__model-ruler__fine-tune-roi-calculator",
      "mcp__model-ruler__eval-cost-calculator",
      "mcp__model-ruler__observability-cost-calculator",
      "mcp__model-ruler__rag-pipeline-cost-calculator",
      "mcp__model-ruler__automation-cost-calculator",
      "mcp__model-ruler__agent-workflow-cost-calculator",
      "mcp__model-ruler__agent-loop-cost-calculator"
    ],
    "deny": []
  }
}

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 model-ruler. Review it before you use it.

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/io.github.helphub369/model-ruler/verify?hash=51ef26b0583686589de4d756c1d9c3a38fefcb88446c460d730e985db008a45e" | jq -e '.changed == false'

Pinned hash 51ef26b05836, from Nov 20, 2026, 21:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.helphub369/model-ruler/changes.xml

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

Badge

Anlyon Radar badge for io.github.helphub369/model-ruler
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.helphub369/model-ruler.svg)](https://radar.anlyon.com/servers/io.github.helphub369/model-ruler)

Source: MCP Registry. Synced Oct 21, 2026, 18:35 UTC.

Model Ruler — AI Cost Calculators MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Model Ruler — AI Cost Calculators MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 12 of which can change, send or delete something, and 0 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 Model Ruler — AI Cost Calculators MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Model Ruler — AI Cost Calculators 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 Model Ruler — AI Cost Calculators MCP server have?

12 tools: 12 write. token-counter, provider-cost-calculator, self-host-breakeven-calculator, context-window-planner, quantization-calculator, fine-tune-roi-calculator, eval-cost-calculator, observability-cost-calculator and 4 more.

Does the Model Ruler — AI Cost Calculators MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Model Ruler — AI Cost Calculators MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Model Ruler — AI Cost Calculators MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.