How to Use the Diese MCP in LangChain

Q: Can I use LangSmith to debug my ERP tool calls?

Yes. Every time your agent calls listsalesinvoices or listbusinessexpenses, the input parameters and raw JSON outputs are tracked in your LangSmith dashboard for easy debugging.

Feed Diese ERP data straight into your LangChain ReAct agents to run project checks and track invoices without leaving your chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diese MCP to LangChain

Create your Vinkius account to connect Diese 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 Diese with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Diese ERP queries with LangChain

Run your multi-step LangChain runs with live data pulled directly from Diese. Your agent can grab active tasks with `list_project_tasks` and immediately pass those IDs to `get_project_details` in the next link of the chain. This setup lets you build actual logic loops inside your LangChain pipeline. If the agent notices overdue items via `list_overdue_erp_tasks`, it can automatically look up the project owner using `list_erp_contacts` and prepare a status report.

Trace financial workflows in LangSmith

Stop guessing why an invoice check failed inside your LangChain pipeline. When your agent calls `list_sales_invoices` or `list_business_expenses` to reconcile accounts, every tool execution, latency metric, and payload gets logged in LangSmith. You see exactly what metadata `get_account_metadata` returned to your LangChain agent. This makes debugging broken ERP runs a matter of checking a clean execution graph instead of digging through raw console logs.

Coordinate resource planning across tools

Combine this MCP Server with database tools in a single LangChain multi-server setup. Your agent can query scheduled allocations using `list_resource_planning` and compare them against your external developer calendars in real time. Finding a specific project is straightforward since your LangChain agent can run `search_projects_by_name` first, then pull the full task list via `list_erp_projects` to verify team availability before assigning new work.

Setup guide

Set up Diese 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 Diese 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({
    "diese-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 Diese 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 Diese. 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 Diese 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 Diese MCP in LangChain

Install langchain-mcp-adapters via pip and initialize the MultiServerMCPClient with your Vinkius endpoint. From there, call get_tools() to pass the ERP tools directly into your create_agent setup.

Yes, that is exactly what LangChain chains are built for. Your agent can start by calling list_erp_projects to get a list of active projects, then loop through each ID to run list_project_tasks and compile a status update.

The Vinkius platform handles the underlying connection, but you should configure your LangChain runnable with retry logic. If get_account_metadata shows you are hitting usage limits, the chain can back off before running more queries.

Yes. Every time your agent calls list_sales_invoices or list_business_expenses, the input parameters and raw JSON outputs are tracked in your LangSmith dashboard for easy debugging.

Your project details, invoices, and expenses never touch external training sets. Vinkius runs the MCP Server in a zero-trust sandbox, so LangChain only receives the specific ERP records needed to execute your immediate query.

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