Model Ruler — AI Cost Calculators

by helphub369 · remote · no sign-in to list tools · v1.0.4 · published by GitHub user helphub369

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

Changes · 12

Compare Registry entry

12 tools: 12 change things.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things12Claude Code: ask: see these tools
Only reads0Claude Code: allow

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

12 tools

Changes things 12Creates or changes something that can be changed back.Claude 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.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, 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. It assumes the server is installed as model-ruler. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

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

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

Anlyon alternative

12 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 other servers for the same product.

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

For agents: Markdown · JSON · report this listing