How to Use the Unanet MCP in LangChain

Q: Can I use LangChain to analyze project data from Unanet?

Absolutely. You can chain projects with expenses. For instance, you might start by listing all projects and then attach the associated expense reports to each one for a full cost breakdown.

Q: What if I need to track user changes in Unanet using LangChain?

You can monitor changes by chaining users with timesheets. The agent will first get the list of users, then check their corresponding timesheets. This helps you audit who was active and when.

Q: What kind of data does this MCP Server touch regarding user records?

The server exposes employee details through the users tool, providing names and basic roles necessary for tracking internal personnel information.

Build multi-step agents that navigate Unanet data using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unanet MCP to LangChain

Create your Vinkius account to connect Unanet 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 Unanet with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain: Chain multiple actions across the MCP Server

You connect `projects` and `users` to build complex reasoning chains. For example, an agent can first list all active projects, then use those project IDs to fetch every user assigned to them. This allows your AI client to execute multi-step logic. The output from fetching a user's payroll data becomes the input for calculating total allocated expenses.

Fetching employee information with `users`

`users` lets your agent fetch details on any employee in Unanet. You can start by getting a list of all active staff members and then filter that list based on department or status. This is essential for the initial steps of an automation pipeline. The data you get here feeds directly into other tools, like finding associated timesheets.

Tracking job costs using `timesheets`

`timesheets` provides detailed records of time logged against specific users and projects. Your agent can list timesheets for a given user over a date range. This data is critical because you often need to aggregate time entries before calculating project profitability. You're not just listing; you're setting up the next step in your chain.

Setup guide

Set up Unanet 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 Unanet 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({
    "unanet-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 Unanet 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 Unanet. 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 Unanet 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 Unanet MCP in LangChain

LangChain builds these workflows using ReAct agents. The agent doesn't just call a tool; it decides which tools to call and in what order based on the results of previous calls. This makes multi-step reasoning possible.

Absolutely. You can chain `projects` with `expenses`. For instance, you might start by listing all projects and then attach the associated expense reports to each one for a full cost breakdown.

You can monitor changes by chaining `users` with `timesheets`. The agent will first get the list of users, then check their corresponding timesheets. This helps you audit who was active and when.

Yes, the setup supports aggregating tools from multiple servers into a single agent framework instance. You'll need to use `MultiServerMCPClient` for that.

The server exposes employee details through the `users` tool, providing names and basic roles necessary for tracking internal personnel information.

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