Tools MCP Server
An MCP server that provides utility tools for markdown processing, including ADF-to-markdown conversion, table formatting, and table of contents management.
README
Tools MCP Server
An MCP (Model Context Protocol) server that exposes a collection of utility tools for AI agents. This modular server allows agents to perform complex operations through well-defined tool interfaces.
Features
Markdown Collection
- ADF to Markdown: Convert Atlassian Document Format (ADF) to Extended Markdown
- Markdown to ADF: Convert Extended Markdown to Atlassian Document Format
- Table Formatting: Format tables with aligned columns for human readability
- TOC Management: Generate and refresh table of contents based on document headings
Supports all ADF elements including panels, tables, media, mentions, code blocks, and more.
Installation
npm install
npm run build
Claude Desktop Setup
Add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"toolkit": {
"command": "node",
"args": ["/absolute/path/to/tools-mcp-server/build/index.js"]
}
}
}
Important: Use absolute paths, not relative paths.
After updating the configuration, fully quit Claude Desktop (Cmd+Q on macOS) and reopen it.
Claude Code Setup
Global Configuration (recommended)
Edit ~/.claude.json and add the server under the mcpServers key. This makes the server available in all projects without per-project approval prompts:
{
"mcpServers": {
"toolkit": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/tools-mcp-server/build/index.js"]
}
}
}
Project Configuration
Alternatively, add a .mcp.json file to your project root for project-specific access:
{
"mcpServers": {
"toolkit": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/tools-mcp-server/build/index.js"]
}
}
}
After adding the config, restart Claude Code (exit then claude).
Available Tools
Markdown Collection
| Tool | Description | Parameters |
|---|---|---|
markdown_adf_to_markdown |
Convert ADF JSON to Extended Markdown | adf (ADF document object) |
markdown_markdown_to_adf |
Convert Extended Markdown to ADF JSON | markdown (string) |
markdown_format_tables |
Format tables with aligned columns | markdown (string) |
markdown_refresh_toc |
Refresh existing TOC to match current headings | markdown (string), minLevel?, maxLevel? |
markdown_generate_toc |
Generate TOC from headings (without inserting) | markdown (string), minLevel?, maxLevel? |
markdown_insert_toc |
Replace /toc markers with generated TOC |
markdown (string), minLevel?, maxLevel? |
markdown_format |
Combined formatting (tables + /toc + TOC refresh) | markdown (string), formatTables? (bool), processTOC? (bool) |
Usage Examples
Once configured, you can ask Claude:
- "Convert this Confluence ADF to markdown"
- "Transform this markdown into ADF format for Jira"
- "Parse this ADF document and give me the markdown equivalent"
- "Format the tables in this markdown file"
- "Refresh the table of contents"
- "Generate a TOC for this document"
Example: ADF to Markdown
{
"name": "markdown_adf_to_markdown",
"arguments": {
"adf": {
"type": "doc",
"version": 1,
"content": [
{
"type": "paragraph",
"content": [
{ "type": "text", "text": "Hello " },
{ "type": "text", "text": "World", "marks": [{ "type": "strong" }] }
]
}
]
}
}
}
Returns: Hello **World**
Example: Markdown to ADF
{
"name": "markdown_markdown_to_adf",
"arguments": {
"markdown": "# Heading\n\nThis is a **bold** statement."
}
}
Returns a complete ADF document structure.
Example: Format Tables
Input:
| Name | Age | City |
|---|---|---|
| Alice | 30 | New York |
| Bob | 25 | Los Angeles |
Output:
| Name | Age | City |
| ----- | --- | ----------- |
| Alice | 30 | New York |
| Bob | 25 | Los Angeles |
Example: Generate TOC
Input document with headings:
# Main Title
## Section 1
### Subsection 1.1
## Section 2
Generated TOC:
- [Main Title](#main-title)
- [Section 1](#section-1)
- [Subsection 1.1](#subsection-11)
- [Section 2](#section-2)
Example: Insert TOC with /toc Marker
Input:
# My Document
/toc
## Introduction
Content here...
## Conclusion
Final thoughts.
Output:
# My Document
- [My Document](#my-document)
- [Introduction](#introduction)
- [Conclusion](#conclusion)
## Introduction
Content here...
## Conclusion
Final thoughts.
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run the server (for testing)
npm start
# Format code
npm run format
# Lint code
npm run lint
Adding New Tool Collections
- Create a new folder under
src/tools/(e.g.,src/tools/json/) - Define your tools array and handler function following the markdown pattern
- Export
toolsarray andhandleToolfunction - Import and register in
src/index.ts
Testing with MCP Inspector
npx @modelcontextprotocol/inspector node build/index.js
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。