Doccler MCP Server

Doccler MCP Server

Enables AI assistants to interact with the Doccler documentation platform, allowing users to query, create, search, generate, publish, and organize documents directly from their IDE.

Category
访问服务器

README

Doccler MCP Server

🚀 Connect your IDE to Doccler - Use AI-powered documentation directly from your development environment.

npm version

What is MCP?

The Model Context Protocol (MCP) is an open standard that allows AI assistants (like Claude, Cursor, VS Code with AI extensions) to connect to external tools and data sources. Doccler's MCP server enables you to:

  • Query your documentation as a single source of truth
  • Create documentation directly from your IDE
  • Search documentation with semantic search
  • Generate documentation from code using AI
  • Publish/unpublish documents
  • Organize documents into spaces

Quick Start

1. Get Your Doccler API Key

  1. Log in to Doccler
  2. Go to SettingsAPI Keys
  3. Click Create New API Key
  4. Copy the key (it's only shown once!)

2. Configure Your IDE

Choose your IDE and add the configuration:

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "doccler": {
      "command": "npx",
      "args": ["-y", "@doccler/mcp-server@latest"],
      "env": {
        "DOCCLER_API_KEY": "doccler_xxxxxxxx_yyyyyyyyyyyyyyyyyyyy"
      }
    }
  }
}

Claude Desktop

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "doccler": {
      "command": "npx",
      "args": ["-y", "@doccler/mcp-server@latest"],
      "env": {
        "DOCCLER_API_KEY": "doccler_xxxxxxxx_yyyyyyyyyyyyyyyyyyyy"
      }
    }
  }
}

VS Code / Antigravity

Add to your MCP settings:

{
  "mcp": {
    "servers": {
      "doccler": {
        "command": "npx",
        "args": ["-y", "@doccler/mcp-server@latest"],
        "env": {
          "DOCCLER_API_KEY": "doccler_xxxxxxxx_yyyyyyyyyyyyyyyyyyyy"
        }
      }
    }
  }
}

3. Restart Your IDE

After adding the configuration, restart your IDE. The Doccler MCP server will be downloaded and started automatically.

Alternative: Global Installation

If you prefer to install globally instead of using npx:

npm install -g @doccler/mcp-server

Then configure your IDE with:

{
  "mcpServers": {
    "doccler": {
      "command": "doccler-mcp",
      "env": {
        "DOCCLER_API_KEY": "doccler_xxxxxxxx_yyyyyyyyyyyyyyyyyyyy"
      }
    }
  }
}

Available Tools

Tool Description
hello_doccler Verify your connection to Doccler
search_docs Search your documentation (keyword + semantic)
create_doc Create new documentation with optional space
generate_doc Generate documentation from code using AI
publish_doc Publish or unpublish a document
get_doc Get the content of a specific document
list_spaces List all available spaces

Usage Examples

Search Documentation

"Search my documentation for authentication"
"Find docs about API endpoints"

Create Documentation

"Create documentation titled 'Getting Started' about how to install the app"
"Create a doc in the API space explaining the user endpoint"

Generate from Code

"Generate documentation for this code: [paste your code]"
"Document this function with examples"

Publish/Unpublish

"Publish the document with slug 'getting-started'"
"Unpublish my-api-guide"

Environment Variables

Variable Description Default
DOCCLER_API_KEY Your Doccler API key (required)
DOCCLER_API_URL API URL (for self-hosted) https://doccler.app/api

Note: DOCCLER_API_URL is only needed for self-hosted instances or development. Production users can omit it.

Troubleshooting

"API Key not configured"

Make sure DOCCLER_API_KEY is set in your IDE's MCP configuration.

"Unauthorized" errors

  1. Check that your API key is valid
  2. Go to Settings → API Keys in Doccler to verify
  3. Create a new key if needed

Server not starting

  1. Ensure Node.js 18+ is installed
  2. Try running manually: npx @doccler/mcp-server
  3. Check your IDE's MCP logs

Support

License

MIT © Doccler

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选