An MCP skill that connects Pi to MiniMax's web-search and image-understanding services. It includes commands for searching current information and describing an image from a file.

It is for web searches, image descriptions, local setup, and interactive use through MiniMax MCP.

It gives the coding agent a documented way to look up recent information or inspect images when those capabilities are needed.

minimax-mcp — Skill for Claude Code and Codex by ameno-/pi-minimax-mcp

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.

Any agent

npx skills add ameno-/pi-minimax-mcp --skill skill

Clone the repo

git clone --depth 1 https://github.com/ameno-/pi-minimax-mcp

Made for: Claude Code, Codex.

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/skills/ameno-/pi-minimax-mcp/skill/github.svg)](https://agentmods.dev/skills/ameno-/pi-minimax-mcp/skill)

Your own site

<a href="https://agentmods.dev/skills/ameno-/pi-minimax-mcp/skill"><img src="https://agentmods.dev/badge/skills/ameno-/pi-minimax-mcp/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ameno-/pi-minimax-mcp/skill"><img src="https://agentmods.dev/badge/skills/ameno-/pi-minimax-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 306 The whole file, excluding the scripts and references it only reads on demand.

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.

Token cost

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	$0.00015	$0.00306
Opus 5.5	$0.00006	$0.00122
Sonnet 5.5	$0.00003	$0.00061
Haiku 4.5	$0.00002	$0.00031

Measured 2mo ago against content hash e3d2b08be9ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

minimax-mcp 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 2mo 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.

skill/SKILL.md · 63 lines

What it actually says

MiniMax MCP Skill

Web search and image understanding via MiniMax's Model Context Protocol.

Tools

web_search

Real-time web search for up-to-date information.

Usage:

Search for latest React server components documentation

understand_image

Analyze and describe image content.

Usage:

What does this image show? [path/to/image.png]

Setup

Get API key from https://platform.minimax.io/subscribe/coding-plan

Set environment variable:

export MINIMAX_API_KEY="your-api-key"
export MINIMAX_API_HOST="https://api.minimax.io"  # optional

Configuration

Config file: ~/.pi/agent/extensions/minimax-mcp.json

{
  "apiKey": "your-api-key",
  "apiHost": "https://api.minimax.io",
  "basePath": "/tmp/minimax-output",
  "resourceMode": "url"
}

CLI Usage

# Direct search
pi-minimax-mcp search "quantum computing latest breakthroughs"

# Image understanding
pi-minimax-mcp understand ./screenshot.png

# Interactive mode
pi-minimax-mcp interactive

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.

2mo ago First seen · 63 lines · 15 tokens per session scan A e3d2b08be9ae

Subscribe to this mod's changes

minimax-mcp is a skill published in the GitHub repository ameno-/pi-minimax-mcp (2 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 306 once invoked, about $0.0001 per session on Opus 5.5. 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.

Data and AI Research image mcp minimax search

minimax-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
minimax-mcpameno-/pi-minimax-mcp	Skill	2	9mo ago	MIT	A	15	Claude Code, Codex
minimax-cliLingtai-AI/lingtai	Skill	510	19d ago	Apache-2.0	A	72	Claude Code, Codex
vs-search-tuningvolcengine/SearchCLI	Skill	1.2k	22d ago	Apache-2.0	A	29	Claude Code, Codex
frontmcp-extensibilityagentfront/frontmcp	Skill	148	yesterday	Apache-2.0	A	124	Claude Code, Codex
solr-querygriddynamics/rosetta	Skill	370	yesterday	Apache-2.0	A	27	Claude Code, Codex
tao-train-image-classificationNVIDIA-TAO/tao-skill-bank	Skill	99	yesterday	Apache-2.0	A	103	Claude Code
tao-generate-referring-expressionsNVIDIA-TAO/tao-skill-bank	Skill	99	yesterday	Apache-2.0	A	143	Claude Code