How to Use the Dext MCP in LangChain

Q: How do I connect the Dext MCP server to LangChain?

Install langchain-mcp-adapters via pip. You initialize MultiServerMCPClient with your HTTP transport settings and pass the tools directly to your ReAct agent.

Q: Can LangChain filter Dext receipts by keyword?

Yes. The searchinboxbykeyword tool takes supplier names or descriptions and returns matching records. Your agent can use this to audit specific vendors on demand.

Q: Does LangChain track my Dext API rate limits?

Your code handles the logic. You can call getaccountmetadata to check your usage limits before running a massive batch job. LangSmith will track the latency of those calls.

Q: Can I use this Dext MCP integration for multiple clients?

The listaccountingclients endpoint exposes every account under your partner umbrella. You just pass the target client ID into your subsequent tool calls.

Build multi-step accounting pipelines that chain Dext invoice extraction directly into your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to LangChain

Create your Vinkius account to connect Dext 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 Dext with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Dext inbox parsing to LangChain agents

The `list_inbox_items` tool pulls your raw receipt feed straight into your agent's context window. Your LangChain setup takes those raw ledger entries and decides what to do next. If a receipt looks suspicious, the agent triggers `get_item_details` to pull the exact line items. You get full observability in LangSmith for every API call. When an agent loops through fifty invoices, you see exactly how many tokens it burned and how long Dext took to respond. This MCP server turns a messy inbox into a predictable data pipeline.

Route pending receipts to the right approvers

The `list_items_pending_review` tool exposes every invoice stuck in limbo. You write a ReAct agent that grabs this list daily and figures out who needs to sign off. From there, the agent calls `list_account_users` to match the invoice department with an actual human. It pings them on Slack, waits for approval, and moves on. Your accounting workflow stops waiting on manual data entry.

Map supplier data across multiple client accounts

The `list_accounting_clients` tool lets your multi-tenant agents jump between different partner accounts without swapping API keys. Your pipeline grabs a specific client ID and immediately pulls their custom chart of accounts via `list_accounting_categories`. This means your agent automatically knows which tax codes belong to which business. When `list_extracted_suppliers` returns a new vendor, your code maps it to the correct ledger category on the first try.

Setup guide

Set up Dext 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 Dext 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({
    "dext-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 Dext 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 Dext. 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 Dext 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 Dext MCP in LangChain

Install `langchain-mcp-adapters` via pip. You initialize `MultiServerMCPClient` with your HTTP transport settings and pass the tools directly to your ReAct agent.

Yes. The `search_inbox_by_keyword` tool takes supplier names or descriptions and returns matching records. Your agent can use this to audit specific vendors on demand.

Your code handles the logic. You can call `get_account_metadata` to check your usage limits before running a massive batch job. LangSmith will track the latency of those calls.

The `list_accounting_clients` endpoint exposes every account under your partner umbrella. You just pass the target client ID into your subsequent tool calls.

Your agent processes raw invoice line items and bank statement data in memory. LangChain drops the context after the chain executes unless you explicitly log it to LangSmith. The MCP architecture ensures your Dext token stays out of the LLM prompt entirely.

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