How to Use the Daftra MCP in LangChain

Q: How do I connect Daftra to LangChain?

Install the langchain-mcp-adapters package first. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint, then pass the tools from client.gettools() to your ReAct agent.

Q: Can LangChain agents search for Daftra clients?

Yes. The agent uses searchclientsbyname to find matching profiles based on keyword inputs. It parses the returned list and extracts the correct client ID for subsequent operations.

Q: How do I handle pagination for large lists?

Your agent handles it dynamically. When listclients returns a truncated array, the LLM reads the metadata and requests the next batch automatically.

Build multi-step ERP reasoning pipelines. Connect Daftra to your LangChain agents for autonomous accounting operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to LangChain

Create your Vinkius account to connect Daftra 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 Daftra with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Daftra tools in LangChain

`create_client` initiates your accounting workflow by adding a new customer record to the ERP database. This MCP Server exposes the mutation directly to your code. Your ReAct agent decides what happens next based on the returned client ID. It might immediately trigger a follow-up action or pass that ID to another node in your graph. You get full visibility into this process through LangSmith. Tracing shows exactly how long the API took to respond and which parameters the agent chose. If a step fails, the agent can loop back and try a different payload.

Query deep financial records

`get_invoice_details` pulls line items, tax rates, and payment history for specific sales transactions. LangChain passes this raw billing data into your prompt template via the MCP protocol. The LLM then parses the line items to answer specific user questions about their spending. Combining this with vector stores happens in a single pipeline. The agent pulls the invoice data, compares it against contracts stored in Pinecone, and flags discrepancies. Everything happens in one execution run.

Manage inventory and expenses

`list_inventory_products` fetches your current product catalog, including pricing and service IDs. Your agent uses this catalog to validate user requests before generating new quotes. It checks the live database instead of relying on outdated context. The same logic applies to outbound cash flow. Calling `list_expenses` returns categorized business costs. Routing these expense arrays through an output parser generates structured financial reports automatically.

Setup guide

Set up Daftra 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 Daftra 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({
    "daftra-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 Daftra 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 Daftra. 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 Daftra 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 Daftra MCP in LangChain

Install the `langchain-mcp-adapters` package first. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint, then pass the tools from `client.get_tools()` to your ReAct agent.

Yes. The agent uses `search_clients_by_name` to find matching profiles based on keyword inputs. It parses the returned list and extracts the correct client ID for subsequent operations.

You can use this MCP integration inside any LangGraph node. State passes between nodes naturally, meaning one step can fetch an invoice and the next can analyze it.

Your agent handles it dynamically. When `list_clients` returns a truncated array, the LLM reads the metadata and requests the next batch automatically.

Vinkius runs the server in an ephemeral V8 isolate sandbox. When your agent pulls tax details and payment history via `get_invoice_details`, the sandbox destroys itself right after the request finishes. Nothing persists in 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