Mini Agent is a small demonstration application for building a single AI agent with the MiniMax M2.5 model, an Anthropic-compatible API, tools, memory, and context handling. It is intended as a starting point for developing and debugging agents, and includes skills and MCP integrations that extend the agent's workflow.
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.
npx skills add MiniMax-AI/Mini-Agent --skill mcp-buildergit clone --depth 1 https://github.com/MiniMax-AI/Mini-AgentWrote 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/skills/minimax-ai/mini-agent/mcp-builder)<a href="https://agentmods.dev/skills/minimax-ai/mini-agent/mcp-builder"><img src="https://agentmods.dev/badge/skills/minimax-ai/mini-agent/mcp-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.02865 |
| Opus 5 | $0.00030 | $0.01432 |
| Sonnet 5 | $0.00012 | $0.00573 |
| Haiku 4.5 | $0.00006 | $0.00286 |
Grade A, and why
mcp-builder 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
- mcp-builder — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Development Guide
Overview
To create high-quality MCP (Model Context Protocol) servers that enable LLMs to effectively interact with external services, use this skill. An MCP server provides tools that allow LLMs to access external services and APIs. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks using the tools provided.
Process
🚀 High-Level Workflow
Creating a high-quality MCP server involves four main phases:
Phase 1: Deep Research and Planning
1.1 Understand Agent-Centric Design Principles
Before diving into implementation, understand how to design tools for AI agents by reviewing these principles:
Build for Workflows, Not Just API Endpoints:
- Don't simply wrap existing API endpoints - build thoughtful, high-impact workflow tools
- Consolidate related operations (e.g.,
schedule_eventthat both checks availability and creates event) - Focus on tools that enable complete tasks, not just individual API calls
- Consider what workflows agents actually need to accomplish
Optimize for Limited Context:
- Agents have constrained context windows - make every token count
- Return high-signal information, not exhaustive data dumps
- Provide "concise" vs "detailed" response format options
- Default to human-readable identifiers over technical codes (names over IDs)
- Consider the agent's context budget as a scarce resource
Design Actionable Error Messages:
- Error messages should guide agents toward correct usage patterns
- Suggest specific next steps: "Try using filter='active_only' to reduce results"
- Make errors educational, not just diagnostic
- Help agents learn proper tool usage through clear feedback
Follow Natural Task Subdivisions:
- Tool names should reflect how humans think about tasks
- Group related tools with consistent prefixes for discoverability
- Design tools around natural workflows, not just API structure
Use Evaluation-Driven Development:
- Create realistic evaluation scenarios early
- Let agent feedback drive tool improvements
- Prototype quickly and iterate based on actual agent performance
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE.txt 11 KB
- reference/evaluation.md 21 KB
- reference/mcp_best_practices.md 28 KB
- reference/node_mcp_server.md 26 KB
- reference/python_mcp_server.md 26 KB
- scripts/connections.py 4.8 KB runs code
- scripts/evaluation.py 12 KB runs code
- scripts/example_evaluation.xml 1.2 KB
- scripts/requirements.txt 29 B
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 · 329 lines · 61 tokens per session scan A b1010e90adcb
mcp-builder is a skill published in the GitHub repository MiniMax-AI/Mini-Agent (3,012 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 2,865 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
langbot-eba-adapter-dev
Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture. Use when adding or migrating Telegram, Discord, or other messaging platform adapters to the EBA adapter layout, validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus…
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
agentfield
Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite…