How to Use the Fieldly MCP in LangChain

Q: How do I run Fieldly tools inside a LangChain agent?

Install the langchain-mcp-adapters package and instantiate the MultiServerMCPClient pointing to your Vinkius endpoint. Pass the tools from client.gettools() directly into your agent constructor to let it call Fieldly APIs.

Run multi-step construction workflows by connecting Fieldly to your LangChain agent chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fieldly MCP to LangChain

Create your Vinkius account to connect Fieldly 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 Fieldly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain work items and bookings in LangChain

The `list_work_items` tool lets your agent pull active construction jobs and feed them directly into scheduling steps. In a LangChain setup, the output of this tool flows straight to `list_bookings` to find open slots without writing custom glue code. Your agent checks the status of current projects and maps them to the calendar. You get full observability over this tool chain using LangSmith. If a step fails while matching jobs to workers, you see exactly what raw payload came from Fieldly. This prevents broken pipelines when scheduling field crews.

Trace Fieldly MCP Server invoice pipelines

The `list_invoices` tool retrieves financial records so your LangChain pipeline can match them against jobs. Your agent uses the tool to gather unpaid balances, then triggers `get_invoice` for specific breakdowns. This moves your billing operations from manual lookups to automated, trace-backed workflows. Every tool execution shows up in your LangSmith dashboard with precise latency metrics. You know exactly how long the Fieldly MCP Server takes to fetch invoice histories before passing them to the next chain link.

Check field resources via active chains

The `list_users` tool exposes your active field staff directory directly to LangChain reasoning loops. Your agent queries this list to identify available crew members, then calls `get_booking` to check their current site assignments. This eliminates double-booking errors before they reach the job site. By combining these tools with LangChain memory, your agent retains context across long-running scheduling conversations. It remembers which technician was queried in the previous step when creating a new job card.

Setup guide

Set up Fieldly 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 Fieldly 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({
    "fieldly-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 Fieldly 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 Fieldly. 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 Fieldly 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 Fieldly MCP in LangChain

Install the `langchain-mcp-adapters` package and instantiate the `MultiServerMCPClient` pointing to your Vinkius endpoint. Pass the tools from `client.get_tools()` directly into your agent constructor to let it call Fieldly APIs.

Yes, you can build multi-step chains where the agent first calls `list_work_items` and then uses the results to execute `create_work_item`. LangChain handles the passing of parameters between these tools automatically.

Use LangSmith tracing to inspect the exact inputs and outputs of tools like `get_booking` or `get_invoice`. You will see the raw JSON payloads and execution latency for every step in the chain.

Yes, you can pass the Fieldly tools to LangGraph state charts. This allows your graph nodes to make decisions based on data returned from `list_customers` or `list_users`.

Your scheduling bookings and financial invoices never pass through third-party servers. Vinkius runs the Fieldly MCP Server in a zero-trust, ephemeral V8 sandbox that isolates your data and handles authentication securely.

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