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.
git clone --depth 1 https://github.com/madebyaris/rakitui-aiWrote 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.
[](https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-mcp-tools)<a href="https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-mcp-tools"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/minimax-mcp-tools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-mcp-tools"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/minimax-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03083 | $0.03083 |
| Opus 5 | $0.01541 | $0.01541 |
| Sonnet 5 | $0.00617 | $0.00617 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
minimax-mcp-tools 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax M2.1 MCP Tools Integration
MiniMax provides powerful MCP tools that are ESSENTIAL for reliable code generation. Version checking and verification are not optional.
Critical Workflow: Version Checking
MANDATORY Before Using Any Package
Every time you need to use a package/library:
<think>
[VERSION CHECK REQUIRED]
Package: [package-name]
Current date: [get from context, e.g., December 2024]
Framework context: [what framework/project]
Step 1: Web search for current version
Step 2: If unclear, use Context7
Step 3: Verify compatibility with project
</think>
Version Check Execution Pattern
// Step 1: Always include current month and year in search
→ web_search("react latest stable version December 2024")
→ web_search("next.js 15 vs 14 which stable December 2024")
→ web_search("tailwindcss npm latest version 2024")
// Step 2: If web search is inconclusive
→ resolve-library-id(libraryName="react")
→ get-library-docs(context7CompatibleLibraryID="/facebook/react", topic="installation")
// Step 3: Check compatibility
→ web_search("react 19 next.js 15 compatibility issues 2024")
When to Check Versions
| Situation | Action |
|---|---|
| New project creation | Check ALL major dependencies |
| Adding new package | Check package + peer dependencies |
| User mentions library | Verify current stable version |
| Build/runtime error | Check for version conflicts |
| Migration/upgrade | Check breaking changes |
Tool Call Formatting
CRITICAL: Proper JSON Format
When calling MiniMax MCP tools:
- Use proper JSON - Arguments must be valid JSON strings
- Escape special characters - Quotes, newlines, and backslashes must be escaped
- Don't include thinking blocks -
<think>content goes BEFORE the tool call - Keep queries simple - 3-5 keywords work best
Correct format:
{
"query": "React 19 hooks documentation December 2024"
}
Incorrect (will cause error 400/2013):
{
"query": "→ search for React 19 <think>need docs</think>"
}
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.
- 10d ago First seen · 504 lines · 3,083 tokens per session scan A 303f184d6d09
minimax-mcp-tools is a cursor rule published in the GitHub repository madebyaris/rakitui-ai (5 stars, last pushed 7mo ago), licensed MIT. It adds 3,083 tokens to every session, about $0.0154 per session on Opus 5. 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.
Other cursor rules, from other repositories
AIRules
NexusLink MCP four-step workflow and prohibitions (copy to project .cursor/rules/ and fill the project-specific section).
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.