Why it is worth attention

It encourages honest disclosure of side-effectful tools and danger levels, with configurable language, length, transport, and danger options to produce security-aware MCP server documentation.

Who it is for

Developers publishing MCP servers
Maintainers refreshing MCP repository documentation
Teams needing client mcpServers config snippets
Technical writers documenting MCP tool safety

Use cases

Drafting or refreshing an English, Chinese, or bilingual README for an MCP server
Documenting write/exec tools and their side effects with danger levels
Generating paste-ready client mcpServers configuration snippets
Adding auth, environment placeholders, and security notes to MCP server docs

Strengths

Offers configurable options for lang, length, transport, and danger level
Delivers a complete README draft plus tools and security tables
Supports multiple transport types: stdio, sse, http, and multi
MIT-licensed and installable via npx skills add

Considerations

Only targets MCP server repositories, not generic libraries
Does not implement the server itself or provide exploit guidance
Danger level is selected manually via an option rather than assessed automatically

README quick start

MCP Server README

Public MCP Server README: capability boundaries, auth, install, and dangerous-tools disclosure.

中文简介： MCP Server 公开 README（能力边界、鉴权、危险工具声明）。 — 详见 README.zh.md.

What this skill does

Drafts an EN-primary README for one MCP server
Documents tools with side effects and danger levels
Spells out auth, env placeholders, and security notes
Gives paste-ready client mcpServers config snippets

Install

npx skills add / --skill mcp-server-readme

Local monorepo: skills/mcp-server-readme/.

Options

Option	Values	Default
`lang`	`en` · `zh` · `bilingual`	`en`
`length`	`minimal` · `standard` · `full`	`standard`
`transport`	`stdio` · `sse` · `http` · `multi`	`stdio`
`danger`	`none` · `some` · `high`	`some`

When to use

Use	Don't
Publish/refresh an MCP server repo	Non-MCP generic library only
Disclose write/exec tools honestly	Hide admin tools “for simplicity”
Client install JSON	Implement the server or write exploits

Deliverable

Complete public README draft + tools/security tables.

See SKILL.md.

Example

../../output/samples/mcp-server-readme-example-01.md

License

MIT — see LICENSE.

Related repositories

Similar projects matched by category, topics, and programming language.

mereyabdenbekuly-ctrl

Featured

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents

859

0xwilliamortiz

Featured

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models

577

MoonshotAI

Featured

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents

3,348