mcp-Docuplete

mcp-Docuplete

Docuplete automates document completion for businesses — PDF templates, client interview forms, and e-signatures in one platform. The MCP server lets you drive the entire workflow from a conversation: find your document packages, start a client session, prefill fields from context, and generate the completed PDF packet without touching the dashboard.

Category
访问服务器

README

@docuplete/mcp-server

Docuplete

Official Model Context Protocol (MCP) server for Docuplete — control document automation from Claude Desktop, Cursor, and any MCP-compatible AI client.


What it does

This server exposes Docuplete's document-filling and PDF-generation capabilities as MCP tools, letting you ask your AI assistant things like:

  • "List my available document packages"
  • "Create a session for the IRA Rollover package and pre-fill Jane Smith's name"
  • "Check if session df_abc123 is complete"
  • "Generate the PDF for session df_abc123 and give me the download link"

Quick start (npx)

DOCUPLETE_API_KEY=sk_live_... npx @docuplete/mcp-server

Installation

Claude Desktop

Add the following to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "docuplete": {
      "command": "npx",
      "args": ["-y", "@docuplete/mcp-server"],
      "env": {
        "DOCUPLETE_API_KEY": "sk_live_YOUR_KEY_HERE"
      }
    }
  }
}

Restart Claude Desktop — you'll see the Docuplete tools available in the tool panel.

Cursor

Add the following to .cursor/mcp.json in your project (or ~/.cursor/mcp.json globally):

{
  "mcpServers": {
    "docuplete": {
      "command": "npx",
      "args": ["-y", "@docuplete/mcp-server"],
      "env": {
        "DOCUPLETE_API_KEY": "sk_live_YOUR_KEY_HERE"
      }
    }
  }
}

Authentication

Get your API key from the Docuplete dashboard under Settings → API Keys.

API keys are prefixed with sk_live_. Store them in environment variables — never hard-code them.


Available tools

Tool Description Required inputs
list-packages List all document packages on your account
get-package Get full details for a specific package packageId
create-session Start a new interview session and get the interview URL packageId
get-session Check the status of a session (poll for completion) token
generate-pdf Finalise a session and generate the PDF packet token
list-sessions List recent sessions with optional filters

Tool details

list-packages

Returns all packages configured on the account with their IDs and names.

get-package

Input Type Required Description
packageId number yes Numeric package ID

create-session

Input Type Required Description
packageId number yes Package to use
prefill object no Key-value pairs to pre-populate form fields
recipientEmail string no Email of the person completing the interview
transactionScope string no Label describing the transaction
source string no Label identifying where this session came from

Returns the session token and interviewUrl.

get-session

Input Type Required Description
token string yes Session token from create-session

Session status values: draftin_progressgenerated.

generate-pdf

Input Type Required Description
token string yes Session token

Returns a downloadUrl for the completed PDF packet.

list-sessions

Input Type Required Description
packageId number no Filter to a specific package
status string no Filter by status: draft, in_progress, or generated
limit number no Max results (default 50)
offset number no Offset for pagination

Example workflow

Ask your AI assistant:

"Use Docuplete to create an IRA rollover document session for Jane Smith (jane@example.com) and give me the link."

The assistant will:

  1. Call list-packages to find the IRA rollover package
  2. Call create-session with Jane's details pre-filled
  3. Return the interview URL for you to share

Get your API key

Sign up or log in at docuplete.com and go to Settings → API Keys to create your key.


License

MIT

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