How to Use the Documint MCP in LangChain

Q: How do I pass Documint template schemas to a LangChain agent?

You feed the gettemplateconfiguration tool directly to your agent. The agent reads the field schema, maps your application data to the required variables, and calls createnewgeneration to build the PDF.

Q: Do I need to write custom code to map variables?

No. The agent uses gettemplatevariableaudit to inspect the template dynamically, letting LangChain handle the mapping schema on the fly.

Generate custom PDFs inside your LangChain reasoning loops without manually mapping templates or writing rendering code.

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 LangChain

Create your Vinkius account to connect Documint 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 Documint with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step LangChain Document Pipelines

LangChain agents can now inspect your document layouts before triggering a build. Your agent calls `get_template_configuration` to inspect the schema, runs a quick validation step, and then executes `create_new_generation` to produce the PDF. This turns a multi-step document workflow into an autonomous loop where the model corrects its own inputs. You can track these tool executions directly in LangSmith to watch how your chain handles variables. If a variable is missing, the agent uses `get_template_variable_audit` to identify the gap, fixes the payload, and retries the generation.

Automated Template Selection

Stop hardcoding template IDs in your chain configurations. Your LangChain agent uses `search_documint_templates` to locate the correct invoice or contract template based on user prompts. After finding the right template, the agent grabs the exact schema using `list_documint_templates` to prepare the payload. This dynamic discovery keeps your code clean and your chains flexible. You don't need to rebuild your graph when marketing updates a template in Documint; the agent adapts at runtime.

Real-Time Generation Tracking and Recovery

By exposing these tools through an MCP Server, your agent can pause, verify the document status, and retrieve the download URL. It handles the entire verification step natively without requiring manual polling scripts in your application code. If something breaks during a high-volume run, the agent inspects `list_failed_doc_generations` to isolate the bad payloads. This lets your graph handle failures gracefully by sending the bad inputs back to a correction node instead of crashing the entire chain.

Setup guide

Set up Documint 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 Documint 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({
    "documint-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 Documint 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 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 LangChain

You feed the `get_template_configuration` tool directly to your agent. The agent reads the field schema, maps your application data to the required variables, and calls `create_new_generation` to build the PDF.

Yes, you can design a fallback path in your LangGraph chain. The agent checks `list_failed_doc_generations` to find errors, corrects the payload, and executes the call again.

LangSmith traces every tool call made by this MCP Server, showing you the exact inputs sent to `create_new_generation`. You can inspect latency, verify payload schemas, and see exactly where a PDF generation failed.

No. The agent uses `get_template_variable_audit` to inspect the template dynamically, letting LangChain handle the mapping schema on the fly.

Your template variables and generated PDF URLs go directly between your LangChain environment and the Documint API. Vinkius runs this server in an isolated, zero-trust sandbox, meaning your raw document payload is never cached or stored on our servers.

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