Model Advisor MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Model Advisor MCP Help me pick a Claude model for translating a short WhatsApp message."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🧭 Model Advisor
Stop wasting your Claude usage. Get a one-line tip on which model to use for each task.
Using the most powerful model for everything burns through your limits fast. A translation doesn't need Opus, and a full product spec shouldn't be done on Haiku. Model Advisor tells you which one fits, at the start of a task, and tells you at the end if a cheaper model would have done the job.
Free and open source. Built by SigmaMax AI Solutions.
💡 Honest note: Claude can't switch models for you. Model Advisor gives the advice; you pick the model in Claude's model selector.
Model | Best for |
Haiku 5.5 | Quick and short: rephrase, translate, format, quick facts |
Sonnet 5.5 (default) | Everyday work: emails, outreach, proposals, research, calculations, normal coding |
Opus 5.5 | Complex work: build specs, architecture, strategy, contracts, hard debugging |
Fable 5.1 | Only the hardest problems, after Opus falls short |
🚀 Start here: pick your path
You use... | Use this | Setup time |
Claude.ai (web or phone) | Path 1: add as a connector (easiest) | 1 minute, no install |
Claude.ai (free plan) | Path 2: paste instructions | 2 minutes, nothing to install |
Claude Desktop, Claude Code, Antigravity, Cursor | Path 3: local MCP server | 10 minutes |
Path 1: Add as a connector (easiest, works on phone too)
Open claude.ai in a browser and go to Settings → Connectors → Add custom connector.
Name:
Model Advisor. URL:https://model-advisor-mcp.vercel.app/mcpClick Add, then switch it on from the tools menu in a chat.
Try: "Use recommend_model: translate this WhatsApp line into Arabic. I'm on Opus."
Add it once on the website and it appears in the Claude phone app on the same account. Note: custom connectors may need a paid Claude plan. On a free plan, use Path 2.
Path 2: Paste instructions (Claude.ai, no install)
In Claude, create a Project (or open Settings and find your personal preferences).
Paste this into the project instructions:
At the start of each new task, add ONE line at the top of your reply recommending the best Claude model for it:
"🧭 Model: <current> fits ✅" or "🧭 Model tip: switch to <model> — <reason, 10 words max>".
Guide: Haiku = quick/short/mechanical (translate, rephrase, format). Sonnet = default for everyday work (emails, research, calculations, normal coding). Opus = complex multi-step reasoning, build specs, architecture, strategy, contracts, hard debugging. Fable = only the hardest problems after Opus fell short.
At the end of a big task, add "🧭 Next time: <model> would be enough" only if a lighter model clearly would have done. If the chat is very long and the topic changed, suggest a new chat. Skip all of this for quick follow-ups.Start any chat inside that project. Done.
Prefer a Claude skill? The same thing is packaged in skills/model-advisor/SKILL.md.
Path 3: Local MCP server (Claude Desktop, Claude Code, Antigravity)
Needs Node.js 18+ and Git.
git clone https://github.com/ahsanmassgazal-cmd/model-advisor-mcp.git
cd model-advisor-mcp
npm install
npm test # should print: 12/12 recommendation cases passedAdd it to your MCP config. For Claude Desktop, open the config file:
Windows: press
Win+R, type%APPDATA%\Claude, openclaude_desktop_config.jsonMac:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"model-advisor": {
"command": "node",
"args": ["C:\\Users\\YOU\\model-advisor-mcp\\src\\index.js"]
}
}
}Use the real full path to src/index.js. On Windows, double every backslash (\\). On Mac, use /Users/you/model-advisor-mcp/src/index.js. If the file already lists other servers, add model-advisor inside the existing mcpServers block.
Fully quit and reopen Claude Desktop. Claude Code: claude mcp add model-advisor -- node /full/path/to/src/index.js. Antigravity / Cursor: add the same node command and path in the MCP settings.
Make it automatic: add this to your custom instructions so Claude calls it by itself:
At the start of each new task, call
recommend_modeland show itsone_liner. At the end of a substantial task, callreview_model_choiceand show the note only if it suggests a change.
Related MCP server: claude-cost-mcp
🧪 Try it: examples
Just ask in plain words. Real outputs:
You say | Model Advisor replies |
"Use recommend_model: translate this WhatsApp line into Arabic" (on Opus) | 🧭 Model tip: Switch down to Haiku 5.5, Opus 5.5 is more than this needs (saves usage). |
"Draft a LinkedIn outreach message to a logistics CEO" (on Opus) | 🧭 Model tip: Switch down to Sonnet 5.5, Opus 5.5 is more than this needs (saves usage). |
"Write a comprehensive build spec for a multi-agent CRM product" (on Sonnet) | 🧭 Model tip: Switch up to Opus 5.5, Sonnet 5.5 may give weaker results here. |
"Review this founders agreement and flag risky clauses" (on Haiku) | 🧭 Model tip: Switch up to Opus 5.5, Haiku 5.5 may give weaker results here. |
End of a task: "Use review_model_choice: translated one line, used Opus" | 🧭 Next time: Haiku 5.5 would be enough for this kind of task (saves usage). |
A chat that has run 60+ messages | Start a new chat for a new topic to save tokens. |
🔧 Tools (Path 1 and 3)
Tool | When | What you get |
| Start of a task | Best model, a one-line verdict, confidence, tips |
| End of a task | Whether a lighter or stronger model fits next time |
| Any time | The model guide with API ids |
❓ Troubleshooting
Connector fails to add: open the URL in a browser. If you do not see 'Model Advisor MCP is running', the server is down.
Tool doesn't appear in Claude Desktop: the config path or JSON is wrong. Check for single backslashes, missing commas, then fully quit (system tray) and reopen.
nodenot recognized: install Node.js LTS, then reopen your terminal.Web or phone Claude: use Path 1 (connector) or Path 2 (instructions).
How it decides
Defaults to Sonnet, the best balance for most work.
Goes down to Haiku only for short, mechanical tasks.
Goes up to Opus for multi-step reasoning, long precise deliverables, or high-stakes work.
Suggests Fable only when Opus has been tried or the problem is at the frontier.
Runs locally with simple rules: zero API calls, zero tokens. Edit
MODELSandRULESinsrc/advisor.jsto tune it, and add a case intest/test.jsfor each change.
Roadmap
Usage log with a weekly "what you could have saved" summary
Optional LLM-assisted classification for unclear tasks
Team rule presets
License
MIT © SigmaMax AI Solutions
Need AI agents for your business? SigmaMax builds AI agents and automation for companies across the GCC, India and beyond. 🌐 sigmamaxaisolutions.com · ✉️ ahsansigmamaxai@gmail.com · WhatsApp +968 7694 1459
Available Tools
3 toolslist_modelsList Claude models and when to use eachA
Returns the model guide: each Claude model, its API id, and what it is best for.
Inputs: no named parameters.
recommend_modelRecommend a Claude modelB
Call at the START of a new task. Returns which Claude model (Haiku, Sonnet, Opus, Fable) fits the task best, so the user gets good results without wasting usage. Show the returned one_liner to the user.
Inputs: task (required), high_stakes, chat_messages, current_model.
review_model_choiceEnd-of-task model reviewA
Call at the END of a substantial task. Says whether a lighter (or stronger) model would have been better next time. Show the returned note to the user only if change is 'up' or 'down'.
Inputs: task (required), model_used (required), output_size, result_was_good.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool occupies a distinct point in the task lifecycle: recommend_model at the start, review_model_choice at the end, and list_models as a static reference lookup. The descriptions explicitly state when to call each, leaving no realistic chance of misselection.
All three names follow the same verb_noun convention (recommend_model, review_model_choice, list_models) with snake_case throughout. The verbs are also semantically aligned with their described actions.
Three tools is on the lean side, but the domain is narrow (model selection advice) and each tool earns its place. Nothing feels padded or redundant.
The surface covers the advisory loop: reference guide, pre-task recommendation, and post-task review. Minor gaps exist, such as comparing two models head-to-head or retrieving past recommendations, but agents can work around these with list_models.
Maintenance
Related MCP Connectors
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi
Exact Claude API cost calc with real cache economics, plus a tiktoken-misuse scanner.
Multi-brand AI code review for Claude: up to 12 reviewers and a judge, no install.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Claude to delegate coding tasks to local Ollama models, reducing API token usage by up to 98.75% while leveraging local compute resources. Supports code generation, review, refactoring, and file analysis with Claude providing oversight and quality assurance.27AGPL 3.0
- AlicenseAqualityDmaintenanceEstimates Claude API token counts, per-model cost, and prompt-caching break-even without an API key or network.5MIT
- FlicenseNot gradedqualityDmaintenanceRoutes code generation tasks between local models and Claude Cloud, optimizing cost by handling simple tasks locally and reserving cloud thinking for complex tasks.-
- FlicenseNot gradedqualityDmaintenanceEstimates Claude API costs with interactive sliders, live comparison across five models, and returns the selected model to the conversation.-