# Model Ruler — AI Cost Calculators (remote · modelruler.dev)

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

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `modelruler.dev`: 74/100 (this document), [markdown](https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2.md), [page](https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2)

## Channel facts

- Endpoint: `https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.4`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2015 tokens (~167/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Tools include usage examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "eval-cost-calculator" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Model Ruler — AI Cost Calculators MCP server?

Model Ruler — AI Cost Calculators is a hosted endpoint at https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry, 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.

### Claude

```bash
claude mcp add --transport http helphub369-model-ruler 'https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry'
```

### Cursor

```json
{
  "mcpServers": {
    "helphub369-model-ruler": {
      "url": "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "helphub369-model-ruler": {
      "type": "http",
      "url": "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
    }
  }
}
```

### Codex

```toml
[mcp_servers.helphub369-model-ruler]
url = "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "helphub369-model-ruler": {
      "type": "remote",
      "url": "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add helphub369-model-ruler --url 'https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  helphub369-model-ruler:
    url: "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
```

### Netclaw

```json
{
  "McpServers": {
    "helphub369-model-ruler": {
      "Transport": "http",
      "Url": "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
    }
  }
}
```

### Vellum

```bash
assistant mcp add helphub369-model-ruler -t streamable-http -u 'https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry'
```

### Other

```json
{
  "mcpServers": {
    "helphub369-model-ruler": {
      "type": "http",
      "url": "https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-09 (score 68, +1)

- [functional improvement] Stability: unverified → 0.07

### 2026-10-07 (score 67)

First indexed and scored.

## MCP tools (12)

### `token-counter` (~91 tokens)

Token Counter

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.

Input parameters:

- `expected_out_tokens` (number): Expected output token budget (optional)
- `text` (string, required): Text content to count tokens for
- `tokenizer` (string): Tokenizer family (default: default)

### `provider-cost-calculator` (~145 tokens)

LLM Provider Cost Calculator

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.

Input parameters:

- `calls_per_month` (number): Monthly call volume
- `include_comparison` (boolean): Include tier comparison table (default true)
- `model` (string): Target model (e.g. claude-sonnet-4-6)
- `provider` (string): Target provider (e.g. anthropic, openai, together)
- `tokens_in` (number, required): Input tokens per call
- `tokens_out` (number, required): Output tokens per call

### `self-host-breakeven-calculator` (~161 tokens)

Self-Host Breakeven Calculator

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.

Input parameters:

- `api_cost_per_1m_out` (number): Current API output cost per 1M tokens
- `gpu_provider` (string): GPU provider (e.g. runpod, modal)
- `gpu_type` (string): GPU type (e.g. h100, a100-80gb)
- `monthly_tokens` (number, required): Monthly output token volume
- `operational_overhead_pct` (number): Ops overhead % on GPU cost (default 40)
- `utilization_pct` (number): Expected GPU utilization % (default 60)

### `context-window-planner` (~121 tokens)

Context Window Planner

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).

Input parameters:

- `doc_tokens` (number, required): Primary document/content tokens
- `expected_out_tokens` (number): Reserved output budget (default 1000)
- `model_context_window` (number, required): Target model context size
- `overhead_tokens` (number): System prompt + few-shot + history (default 2000)
- `strategy_hint` (string): Preferred strategy (optional)

### `quantization-calculator` (~124 tokens)

Quantization Calculator

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.

Input parameters:

- `batch_size` (number): Serving batch size (default 1)
- `kv_cache_tokens` (number): Max KV cache tokens (default 8192)
- `params_billions` (number, required): Model parameter count in billions
- `precision_from` (string): Starting precision (default bf16)
- `precision_to` (string): Target precision (default int4)

### `fine-tune-roi-calculator` (~163 tokens)

Fine-Tune ROI Calculator

Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.

Input parameters:

- `base_inference_cost_1m` (number): Baseline API output cost per 1M
- `finetuned_inference_cost_1m` (number): Fine-tuned inference cost per 1M
- `monthly_inference_tokens` (number, required): Expected monthly inference volume (output tokens)
- `prompt_reduction_pct` (number): Prompt size reduction % from eliminating few-shot (default 0)
- `train_cost_per_1m` (number): Training cost per 1M tokens
- `train_tokens` (number, required): Training tokens (dataset × epochs)

### `eval-cost-calculator` (~205 tokens)

Evaluation Cost Calculator

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.

Input parameters:

- `avg_tokens_in` (number): Avg input tokens per sample (default 2000)
- `avg_tokens_out` (number): Avg output tokens per sample (default 500)
- `judge_enabled` (boolean): Enable LLM-as-judge second pass (default false)
- `judge_tokens_in` (number): Judge input tokens (default 1500)
- `judge_tokens_out` (number): Judge output tokens (default 200)
- `model` (string): Eval model (default claude-sonnet-4-6)
- `models` (number): Candidate models (default 1)
- `provider` (string): Eval provider (default anthropic)
- `samples` (number, required): Number of eval samples
- `trials_per_sample` (number): Repeats per sample (default 1)

### `observability-cost-calculator` (~95 tokens)

LLM Observability Cost Calculator

Use when a user needs to budget LLM observability tooling. Returns monthly cost at given request volume with retention adjustment.

Input parameters:

- `avg_log_bytes` (number): Avg payload bytes per traced request (default 4096)
- `provider` (string, required): Observability provider
- `requests_per_day` (number, required): Average daily LLM requests
- `retention_days` (number): Retention in days (default 30)

### `rag-pipeline-cost-calculator` (~215 tokens)

RAG Pipeline Cost Calculator

Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation). Returns monthly cost with breakdown and dominant-component identification.

Input parameters:

- `answer_tokens` (number): Avg answer tokens (default 400)
- `chunk_size_tokens` (number): Avg chunk size (default 512)
- `chunks_retrieved` (number): Chunks per query (default 5)
- `corpus_tokens` (number, required): Indexed corpus size in tokens
- `embedding_provider` (string): Embedding model
- `generator_model` (string): Generator model (default claude-sonnet-4-6)
- `generator_provider` (string): Generator LLM provider (default anthropic)
- `queries_per_day` (number, required): User query volume per day
- `question_tokens` (number): Avg question tokens (default 100)
- `reindex_fraction_per_month` (number): Fraction of corpus re-embedded per month (default 0.1)
- `vector_store` (string): Vector store

### `automation-cost-calculator` (~146 tokens)

Workflow Automation Platform Cost Calculator

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.

Input parameters:

- `billable_steps_per_run` (number): Billable actions/modules per run (default 5)
- `make_modules_per_run` (number): Make module actions per scenario run; defaults to billable_steps_per_run
- `workflow_runs_per_month` (number, required): Workflow/scenario runs per month

### `agent-workflow-cost-calculator` (~158 tokens)

Agent Workflow Platform Cost Calculator

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.

Input parameters:

- `agent_runs_per_month` (number, required): Agent workflow runs per month
- `app_actions_per_run` (number): Downstream app actions per agent run (default 3)
- `make_modules_per_run` (number): Make modules per run; defaults to app actions + MCP calls
- `mcp_tool_calls_per_run` (number): MCP tool calls per agent run (default 1)

### `agent-loop-cost-calculator` (~243 tokens)

Agent LLM Loop Cost Calculator

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.

Input parameters:

- `avg_tokens_in_per_turn` (number): Avg input tokens per turn (default 3000)
- `avg_tokens_out_per_turn` (number): Avg output tokens per turn (default 400)
- `context_growth_factor` (number): Multiplier on input tokens as conversation grows (default 1.4)
- `model` (string): LLM model (default claude-sonnet-4-6)
- `provider` (string): LLM provider (default anthropic)
- `steps_per_task` (number): Avg reasoning steps per task (default 5)
- `success_rate` (number): Task success rate 0-1 (default 0.7)
- `tasks_per_month` (number, required): Tasks attempted per month
- `tool_calls_per_step` (number): Avg tool invocations per step (default 2)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2#diagnostics

## Score history

- 2026-10-23: 74
- 2026-10-22: 74
- 2026-10-21: 73
- 2026-10-20: 73
- 2026-10-19: 72
- 2026-10-18: 72
- 2026-10-17: 71
- 2026-10-16: 71
- 2026-10-15: 70
- 2026-10-14: 70
- 2026-10-13: 69
- 2026-10-12: 69
- 2026-10-10: 68
- 2026-10-09: 68
- 2026-10-07: 67

## Common questions

### What is the Model Ruler — AI Cost Calculators MCP server?

Model Ruler — AI Cost Calculators is an MCP server listed in the public MCP registry as io.github.helphub369/model-ruler. Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport. This page covers its hosted endpoint (https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry).

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

Model Ruler — AI Cost Calculators scores 74 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 Model Ruler — AI Cost Calculators MCP server expose?

Model Ruler — AI Cost Calculators exposes 12 tools: token-counter, provider-cost-calculator, self-host-breakeven-calculator, context-window-planner, quantization-calculator, and 7 more. Their descriptions and schemas cost roughly 1,867 tokens of context every time the server is loaded.

### Does the Model Ruler — AI Cost Calculators MCP server require authentication?

No. We connected to Model Ruler — AI Cost Calculators without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Model Ruler — AI Cost Calculators MCP server still maintained?

Model Ruler — AI Cost Calculators is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://modelruler.dev/mcp?dist=model_everywhere_registry_native_official_registry
- Website: https://modelruler.dev/install/?source=official_registry
- Changelog RSS feed: https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2.json
- HTML version of this page: https://verifymcp.io/servers/helphub369-model-ruler/modelruler-2