HotDocs MCP Server for OpenAI Agents SDK 14 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect HotDocs through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="HotDocs Assistant",
instructions=(
"You help users interact with HotDocs. "
"You have access to 14 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from HotDocs"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About HotDocs MCP Server
Connect your HotDocs Advance tenancy to any AI agent and take full control of your document automation workflows through natural conversation.
The OpenAI Agents SDK auto-discovers all 14 tools from HotDocs through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries HotDocs, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Template Discovery — List all template packages and their versions available in your HotDocs tenancy
- Work Item Management — Create, inspect, and manage work items that hold interview data and assembled documents
- Interview Sessions — Initialize interview sessions programmatically for interactive data collection
- Automated Document Assembly — Inject answers via XML and trigger document generation without manual UI interaction
- Document Retrieval — List and download assembled documents (PDFs, Word docs) directly from the agent
- Validation & Auditing — Check unanswered variables, list work items by date range or user, and audit assembly history
The HotDocs MCP Server exposes 14 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect HotDocs to OpenAI Agents SDK via MCP
Follow these steps to integrate the HotDocs MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 14 tools from HotDocs
Why Use OpenAI Agents SDK with the HotDocs MCP Server
OpenAI Agents SDK provides unique advantages when paired with HotDocs through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
HotDocs + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the HotDocs MCP Server delivers measurable value.
Automated workflows: build agents that query HotDocs, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries HotDocs, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through HotDocs tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query HotDocs to resolve tickets, look up records, and update statuses without human intervention
HotDocs MCP Tools for OpenAI Agents SDK (14)
These 14 tools become available when you connect HotDocs to OpenAI Agents SDK via MCP:
complete_assembly
This processes all collected answers and assembles the final documents based on the template configuration. After calling this, the assembled documents become available for download via list_documents and get_document_content. You must have already created a work item, created a version/session, and provided answers (via interview or update_answers). The workItemId and versionId must match an existing work item and its version. Complete document assembly for a work item version
create_interview_session
This endpoint prepares the system to collect answers for the template variables. The response contains interview data needed to render the HotDocs interview UI. Use this before displaying the interview to the user or before assembling documents. The versionId should be unique for each interview session (e.g., v1, v2, or a UUID). Create a new interview session for a work item
create_work_item
A work item is associated with a specific template package and holds answers provided during interviews. You must provide a unique workItemId (alphanumeric identifier you choose) and optionally a templatePackageId. The workItemId becomes the reference for all subsequent operations (interview, assembly, download). IMPORTANT: workItemId must be unique and URL-safe (letters, numbers, hyphens only). Create a new work item in HotDocs Advance
get_auth_token
This is primarily a utility function for debugging authentication issues. The token is used internally by all other tools automatically. If other tools fail with auth errors, verify your credentials are correct. Get a fresh HotDocs API access token
get_document_content
Use this to download the final generated document (PDF, Word, etc.) after assembly is complete. You need the workItemId and the documentId (obtained from list_documents). The response includes the document content and a download URL for direct access. Download/get content of an assembled document
get_template_package
Use the template package ID obtained from list_template_packages. This helps understand the template structure before creating work items. Get details of a specific template package
get_unanswered_variables
This shows which template variables were not provided answers during the interview process. Useful for validating interview completeness before or after document assembly. Requires the workItemId and documentId (from list_documents). The response includes the list of unanswered variables and assembly results. Get unanswered variables from an assembled document
get_work_item
Use this to inspect a work item before or after conducting interviews or assembling documents. The workItemId is the unique identifier you assigned when creating the work item. Get details of a specific work item
list_documents
After completing assembly, this shows all generated documents with their IDs, names, and metadata. Use the document IDs returned here to download individual documents via get_document_content. Each document entry includes filename, creation date, and assembly results information. List all assembled documents for a work item
list_template_packages
Template packages define the structure of documents that can be assembled. Each package contains interview questions and document output configurations. Use this to discover what templates are available for document assembly. The response includes package IDs which are required for creating work items. List all available template packages in HotDocs Advance
list_template_versions
Each template can have multiple versions over time. This shows version history and helps identify which version is currently live/active. Use the package_id from list_template_packages to query versions. List all versions of a template package
list_work_items
You can filter by user ID and/or date range to find specific work items. Leave all parameters empty to list all work items. This is useful for auditing, tracking progress, or finding existing work items to continue working on. Date format should be ISO 8601 (e.g., 2024-01-15 or 2024-01-15T10:30:00). List work items with optional filters
list_work_items_by_date
This is optimized for date-based filtering and auditing. Both fromDate and toDate are required for this tool. Use ISO 8601 date format (e.g., 2024-01-01 or 2024-01-01T00:00:00 for datetime). This is useful for generating reports on document assembly activity over time periods. List work items filtered by a specific date range
update_answers
The answer_xml parameter must contain valid HotDocs answer XML format that matches the template variables. This is useful for automated/batch document assembly where you already have the data. You can call this multiple times to incrementally add answers. Answer XML format example: <AnswerSet><A v="VariableName"><V>Answer Value</V></A></AnswerSet> Update answers for a work item using XML answer format
Example Prompts for HotDocs in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with HotDocs immediately.
"List all available template packages in my HotDocs tenancy."
"Create a new work item 'contract-2024-001' using the employment contract template and assemble a document with these details: employee name is John Smith, position is Software Engineer, start date is March 1st 2024, salary is $95,000."
"Show me all work items created in the last 30 days and check if there are any unanswered variables in the documents."
Troubleshooting HotDocs MCP Server with OpenAI Agents SDK
Common issues when connecting HotDocs to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
HotDocs + OpenAI Agents SDK FAQ
Common questions about integrating HotDocs MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect HotDocs with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect HotDocs to OpenAI Agents SDK
Get your token, paste the configuration, and start using 14 tools in under 2 minutes. No API key management needed.