How to Use the Documint MCP in LlamaIndex

Q: How does LlamaIndex use Documint templates for RAG?

The agent indexes template metadata retrieved from listdocuminttemplates into your vector database. This lets your RAG pipeline search for the right document format before triggering a new generation.

Q: Can I query my Documint generation history using LlamaIndex?

Yes, you can feed listdocumintgenerations into your index. Your agent can then search through past document metadata to find specific files.

Q: How does the LlamaIndex agent handle missing variables?

The agent calls gettemplatevariableaudit to see what fields are missing. It then queries your vector index or database to find the missing values before calling createnewgeneration.

Index your Documint templates and generation logs into LlamaIndex to query your document workflows with natural language.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Documint MCP to LlamaIndex

Create your Vinkius account to connect Documint to LlamaIndex 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 Documint with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Indexing of Documint Templates

This MCP Server lets your agent call `list_documint_templates` and index the structure of every template directly into a vector store. You can then query your layout configurations using natural language. When a user asks to generate a specific invoice, the index queries your template database via `search_documint_templates`. The agent grabs the correct layout without relying on hardcoded lookups.

Grounding LlamaIndex RAG Workflows with Documint Data

Avoid hallucinations by connecting your MCP Server to feed live document logs directly into your query engine. The agent uses `list_documint_generations` to retrieve a list of historical documents. If a customer asks about a recent contract, your LlamaIndex pipeline retrieves the generation details using `get_generation_details`. The agent answers using verified API data instead of guessing.

Live Template Variable Auditing for RAG

Parsing complex PDF structures can break simple RAG pipelines. Your agent uses `get_template_variable_audit` to extract the exact list of variables required for any template. This metadata is indexed dynamically, ensuring your query engine knows exactly what fields are required before calling `create_new_generation`. It guarantees that generated PDFs match your template schemas every time.

Setup guide

Set up Documint MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Documint MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Documint tools.",
)
response = await agent.run("List recent Documint data")

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 Documint. 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 Documint 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 Documint MCP in LlamaIndex

The agent indexes template metadata retrieved from `list_documint_templates` into your vector database. This lets your RAG pipeline search for the right document format before triggering a new generation.

Yes, you can feed `list_documint_generations` into your index. Your agent can then search through past document metadata to find specific files.

The agent calls `get_template_variable_audit` to see what fields are missing. It then queries your vector index or database to find the missing values before calling `create_new_generation`.

You decide where to store the index. The MCP Server merely fetches the live data from Documint, allowing LlamaIndex to process and store it in your local vector database.

Your template schemas and generation logs are fetched via HTTPS directly to your LlamaIndex runner. Vinkius runs the MCP Server in an ephemeral sandbox, ensuring that your customer's PDF metadata and template variables never persist on our infrastructure.

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