How to Use the HotDocs MCP in AutoGen

Q: How do I register the HotDocs tools with AutoGen?

Use the mcpservertools function with StreamableHttpServerParams. Pass the returned list directly into your AssistantAgent constructor.

Q: What happens if an AutoGen agent sends bad XML to the HotDocs MCP Server?

The updateanswers tool will return an error to the chat. A debugging agent can read this error, correct the XML formatting, and retry the submission automatically.

Deploy multi-agent AutoGen teams to debate, assemble, and verify HotDocs legal documents through this MCP Server.

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 AutoGen

Create your Vinkius account to connect HotDocs to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative HotDocs document drafting

The HotDocs MCP Server equips AutoGen conversational teams with the ability to generate real documents. A drafting agent calls `list_template_packages` to select a form, then triggers `create_work_item` to start the process. A separate data-entry agent takes over to map user data into XML. It uses `update_answers` to push the variables, while a compliance agent simultaneously monitors the inputs to ensure no required fields are skipped.

Automate quality control via agent debate

AutoGen shines when agents challenge each other's work. After the drafting agent submits data, a reviewer agent calls `get_unanswered_variables` to check the work item status. If variables are missing, the reviewer rejects the assembly attempt and forces the drafter to fix the XML. Only when both agents reach consensus does the system finally execute `complete_assembly` to finalize the file.

Audit past work items with the MCP Server

You can assign a dedicated auditing agent to monitor system health. This agent routinely runs `list_work_items_by_date` to find stalled interview sessions. It then pulls the details using `get_work_item` and reports back to the group chat. The team discusses why certain templates are failing and adjusts their data ingestion strategies accordingly.

Setup guide

Set up HotDocs MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes HotDocs tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="HotDocs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent HotDocs data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="HotDocs_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent HotDocs data")
    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 AutoGen

The agents communicate in a shared group chat. When one agent creates a session via `create_interview_session`, it posts the resulting ID in the chat history for other agents to use.

Yes. Once the assembly consensus is reached, an agent calls `list_documents` followed by `get_document_content` to retrieve the final file buffer.

Use the mcp_server_tools function with StreamableHttpServerParams. Pass the returned list directly into your AssistantAgent constructor.

The `update_answers` tool will return an error to the chat. A debugging agent can read this error, correct the XML formatting, and retry the submission automatically.

The system processes raw interview XML payloads and active session tokens. All cross-agent communication and endpoint interactions occur locally on your host machine, keeping sensitive input variables out of external logging systems.

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