MCP Scanner

modelruler-inference-calculators

https://modelruler.dev/mcp · scanned 2026-10-17

4 of 12 tools can change data, send it out or run code. That's normal for a useful server, and it's where an approval step helps.

• eval-cost-calculator45 · Medium

  Runs code or commands

  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.

  • Name contains “eval” → runs code or commands
• agent-loop-cost-calculator40 · Medium

  Moves money

  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.

  • Description mentions “billing” → moves money
• agent-workflow-cost-calculator40 · Medium

  Moves money

  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…

  • Description mentions “billing” → moves money
• automation-cost-calculator40 · Medium

  Moves money

  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 inst…

  • Description mentions “billing” → moves money
• token-counter20 · Low

  Touches credentials

  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.

  • Name contains “token” → touches credentials
• context-window-planner18 · Low

  Deletes

  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).

  • Description mentions “truncate” → deletes
• fine-tune-roi-calculator0 · Low

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

• observability-cost-calculator0 · Low

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

• provider-cost-calculator0 · Low

  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.

• quantization-calculator0 · Low

  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.

• rag-pipeline-cost-calculator0 · Low

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

• self-host-breakeven-calculator0 · Low

  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.

Badge for your README

MarkdownCopy

[![Scanned by Vulnify](https://api.vulnify.io/public/mcp-scanner/servers/modelruler-dev-mcp.svg)](https://www.vulnify.io/scanner/modelruler-dev-mcp?utm_source=badge&utm_medium=readme&utm_campaign=scanner-badge)

Automated heuristic result, scanned on 2026-10-17. It is based only on the tool names, descriptions, schemas and annotations this server publishes; no tool was called. It is not a security audit or certification, and not an endorsement of or accusation against the server or its operator. A high score is not a vulnerability finding, and a low score does not mean the server is safe. Vulnify is not affiliated with this server or its operator; names and marks belong to their owners. Server owner? Write to security@vulnify.io from an address at the server's domain to remove or correct this page, or scan it again to update it. We reply within 5 business days.

To exclude your server (and its subdomains) from the scanner and remove its public page, write to security@vulnify.io from an address at its domain. We process requests within 5 business days: the page stops being shown and its stored result is deleted. To fix an error instead, tell us what's wrong or scan the server again.