How to Use the HotDocs MCP in LangChain

Q: Can my LangChain agent tell if a HotDocs template is missing information?

Yes. The agent calls getunansweredvariables after submitting answers. It can then parse that response and ask the user for the exact missing data points.

Build automated document assembly pipelines in LangChain using this MCP Server. Turn raw inputs into finished HotDocs PDFs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HotDocs MCP to LangChain

Create your Vinkius account to connect HotDocs to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup HotDocs with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire up HotDocs assembly chains

The HotDocs MCP Server exposes template discovery and document generation tools directly to your LangChain agents. You build a chain that queries `list_template_packages` to find the right legal form, then immediately pipes that package ID into `create_work_item`. ReAct agents handle the logic routing automatically. If a user provides partial data, the agent calls `update_answers` with the XML payload, then checks `get_unanswered_variables` to decide if it needs to prompt the user for missing details before triggering `complete_assembly`.

Stateful document generation with LangChain

LangChain's memory management pairs perfectly with the session states required by `create_interview_session`. Your agent tracks the `workItemId` across multiple turns, pushing incremental XML updates through `update_answers` as the user chats. You get full observability into this process. LangSmith logs the exact XML payloads sent to HotDocs and tracks the latency of the final `get_document_content` call when the assembled PDF drops into your system.

Query historical workflows via MCP Server

Agents can audit past document assemblies without leaving the LangGraph execution flow. A scheduled chain runs `list_work_items_by_date` to pull all contracts generated yesterday, grabbing the metadata for reporting. The agent then iterates over the results using `list_documents` and `get_document_content` to extract the final files. You string these operations together to build automated nightly backup routines or compliance reports.

Setup guide

Set up HotDocs MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes HotDocs tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hotdocs-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent HotDocs transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by HotDocs Advance. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect HotDocs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about HotDocs MCP in LangChain

Your ReAct agent constructs the XML payload internally and passes it to the `update_answers` tool. LangChain handles the tool calling schema automatically based on the endpoint requirements.

Yes. The agent calls `get_unanswered_variables` after submitting answers. It can then parse that response and ask the user for the exact missing data points.

The tool execution will return an error to the chain. You can configure your agent to catch this and call `get_auth_token` to verify credentials before retrying the assembly.

You can pass the HotDocs tools into the same agent that handles your database or CRM tools. The agent fetches data from your CRM and maps it directly into HotDocs template variables.

The server processes raw XML answer sets and generated PDFs. LangChain only acts as the transport layer, meaning your sensitive legal data passes directly between your runtime environment and the endpoint over HTTPS without third-party storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript