mcp-docs-server
Serves Markdown documentation as an MCP server, enabling AI agents to answer questions from your content. Supports local, npm, and Cloudflare deployment with reusable prompts and resources.
README
mcp-docs-server
Share your knowledge as an MCP server.
Have Markdown files (knowledge) you want to share across workspaces or your company? Run them as an MCP docs server so agents can answer directly from your content.
Make your Markdown docs feel alive in coding agents like Cursor and Claude. Add reusable prompt templates to guide users through common workflows. Expose any file type (JSON, images, configs) as browsable MCP resources. When you're ready to roll it out to your team, publish as an npm package for consistent installs—everyone gets the same version with zero extra setup.
Inspired by Mastra’s excellent Mastra Docs Server, which shows how powerful doc-focused MCP servers can be.
If you're using Cursor, click "Add to Cursor" below to add the mcp-docs-server documentation with one click.
<!-- Primary CTA: Add to Cursor --> <a href="https://cursor.com/en-US/install-mcp?name=mcp-docs-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjaXJjbGVzYWMvbWNwLWRvY3Mtc2VydmVyIl19"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/deeplink/mcp-install-light.svg" /> <img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add to Cursor" /> </picture> </a>
Or add this configuration to your MCP server settings:
{
"mcpServers": {
"mcp-docs-server": {
"command": "npx",
"args": ["-y", "@circlesac/mcp-docs-server"]
}
}
}
Get started
To get up and running quickly, start with the Getting Started guide. It walks through the simple two-file setup and overview of all three deployment modes.
Three ways to serve your docs
- Local STDIO - Use
servefor local development - npm Package - Use
publishto distribute via npm - Cloudflare Worker - Use
cloudflarefor remote deployment
See the Commands Overview for a comparison and detailed guides. For configuration options, see the Configuration Reference. Learn how to create reusable prompt templates for common workflows. Expose any file type as browsable resources. Full documentation: docs/index.md.
Contributing
See CONTRIBUTING.md for local setup, testing, and release notes.
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。