How to Use the HotDocs MCP in CrewAI

Q: How do CrewAI agents handle missing variables in HotDocs?

Your QA agent uses getunansweredvariables to identify missing fields. It then creates a new task for the research agent to extract the missing data from your databases, returning the answers back to the drafting agent to update the XML.

Q: Can CrewAI agents check template version histories?

Yes, a specialized auditor agent can use listtemplateversions to verify if a work item is using the latest legal language. If a newer version is live, the agent can flag the old work item and start a new session.

Deploy specialized CrewAI agent teams to draft, validate, and assemble HotDocs legal packages autonomously.

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 CrewAI

Create your Vinkius account to connect HotDocs to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent template discovery via MCP Server

The `list_template_packages` tool allows your CrewAI research agent to find available document templates in HotDocs Advance. The researcher passes the package details to an analyst agent, who uses `get_template_package` to map out the required variables. This team-based approach ensures that your autonomous crew understands the exact inputs needed before starting a document. By using this MCP Server, the crew shares template metadata across their common memory space.

Autonomous XML answer validation and patching

The `update_answers` tool lets a specialized drafting agent in your CrewAI team write data directly to the HotDocs work item. Meanwhile, your QA agent runs `get_unanswered_variables` to verify the draft before moving to assembly. If the QA agent finds missing information, it tasks the research agent with finding the missing data, then updates the work item. This loop continues autonomously until the XML payload is 100% complete.

Coordinated assembly and delivery pipelines

The `complete_assembly` tool is triggered by the coordinator agent once the drafting crew approves the answers via the HotDocs MCP Server. The coordinator then delegates to a delivery agent, who uses `list_documents` to locate the final files. The delivery agent finishes the operation by calling `get_document_content` to download the PDFs. The crew then logs the completed work item ID using `list_work_items` to update your internal records.

Setup guide

Set up HotDocs MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke HotDocs tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="HotDocs Analyst",
    goal="Access and analyze HotDocs data via MCP.",
    backstory="Expert analyst with direct HotDocs access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent HotDocs transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="HotDocs Analyst",
        goal="Access and analyze HotDocs data via MCP.",
        backstory="Expert analyst with direct HotDocs access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HotDocs transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes, a coordinator agent can monitor multiple sessions by querying `list_work_items`. It can assign different work item IDs to specialized drafting agents, who then run `update_answers` in parallel to speed up high-volume contract drafting.

Your QA agent uses `get_unanswered_variables` to identify missing fields. It then creates a new task for the research agent to extract the missing data from your databases, returning the answers back to the drafting agent to update the XML.

Pass the Vinkius HTTP endpoint URL directly into your CrewAI Agent's `mcps` list. The crew's agents will automatically discover all 14 tools, including `create_work_item` and `complete_assembly`, without requiring manual Python tool definitions.

Yes, a specialized auditor agent can use `list_template_versions` to verify if a work item is using the latest legal language. If a newer version is live, the agent can flag the old work item and start a new session.

The generated Word and PDF documents are retrieved directly from HotDocs Advance via `get_document_content` and are never cached by the MCP Server or Vinkius. Your document content remains strictly within your secure Python execution environment.

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