What is modelcostsaver?

A local tool for estimating the cost of calls to large language models and choosing the least expensive model that can handle a task. MCP is a standard way for an AI agent to use an external tool.

Use it before or during automated AI work that makes model calls. It helps compare expected costs and select a suitable lower-cost model.

It helps reduce unnecessary model spending when several models could do the same job. It works offline, so it does not need keys or network access.

modelcostsaver — MCP server for Claude Code and Codex by sachinuppal

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/sachinuppal/modelcostsaver

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/sachinuppal/modelcostsaver/modelcostsaver.svg)](https://agentmods.dev/mcp/sachinuppal/modelcostsaver/modelcostsaver)

Your own site

<a href="https://agentmods.dev/mcp/sachinuppal/modelcostsaver/modelcostsaver"><img src="https://agentmods.dev/badge/mcp/sachinuppal/modelcostsaver/modelcostsaver.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

modelcostsaver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 10 lines

What it actually says

{
  "modelcostsaver": {
    "command": "npx",
    "args": [
      "-y",
      "@workswarm/modelcostsaver"
    ],
    "env": {}
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 10 lines scan A 2eabf0ad1c61

Subscribe to this mod's changes

modelcostsaver is an MCP server published in the GitHub repository sachinuppal/modelcostsaver (0 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics Cost Optimization Data and AI LLM ai-tools llm-cost mcp model-context-protocol

llm-sidecar

Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required. Runs locally from the llm-sidecar Python package.

awaistechnologist/llm-sidecar · not measured

promptthrift-mcp

MCP server "promptthrift-mcp" as configured in woling-dev/promptthrift-mcp. Runs locally from the promptthrift-mcp Python package.

woling-dev/promptthrift-mcp · not measured

openrouter-multimodal

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP. Runs locally from the @stabgan/openrouter-mcp-multimodal npm package. Needs 13 environment variables to run.

stabgan/openrouter-mcp-multimodal · not measured

mistral

MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch, workflows, sampling, prompts, resources, and Streamable HTTP. Runs locally from the mistral-mcp npm package. Needs 1 environment variable to run.

Swih/mistral-mcp · not measured

mistral-mcp

Mistral AI MCP server: chat, OCR, Voxtral audio, Codestral FIM, vision, agents, batch. Runs locally from the mistral-mcp npm package. Needs 1 environment variable to run.