How to Use the Dashdoc MCP in LangChain

Q: How do I build a multi-step agent for Dashdoc with LangChain?

First, use the MultiServerMCPClient to get the list of Dashdoc tools. Then, pass those tools to a LangChain agent executor, like createagent. The agent will use the tool descriptions to decide which function to call, like using listtransports then gettransportdetails.

Build logistics chains that react to real-time Dashdoc data. Your LangChain agent can now manage your entire fleet.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dashdoc MCP to LangChain

Create your Vinkius account to connect Dashdoc 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 Dashdoc with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain tool calls for multi-step logistics

This isn't about single API calls. Your LangChain agent can now string together operations to solve real problems. It can start by calling `list_transports` to see what's scheduled, then use the output to `get_transport_details` for a specific order that needs attention. From there, it can decide the next logical step. Maybe it needs to check driver availability with `list_fleet_drivers` or find the closest truck using `list_fleet_trucks`. Each tool's output becomes the input for the next, letting your agent reason its way through a complex dispatch problem from start to finish.

Manage your fleet and address book

Give your agent direct control over your Dashdoc assets. It can get a full picture of your operation by calling `list_fleet_trucks`, `list_fleet_trailers`, and `list_fleet_drivers`. This gives it the raw data to figure out vehicle capacity, trailer types, and driver assignments. Your agent can also manage locations. It checks `list_saved_addresses` to see if a pickup point is already in the system. If it's not, the agent uses `create_new_address` to add the new site, complete with gate codes and contact info, returning the new ID for the next step in its chain.

Build a smarter Dashdoc MCP Server agent

Connect your agent to Dashdoc and let it handle the busywork. It can find any order with a partial customer reference using `search_transports_by_reference`. It can also identify who's who by pulling contact info and tax IDs with `list_transport_contacts`. This MCP server gives your agent the functions it needs to act like a junior dispatcher. You define the goal, and the agent chains together the right Dashdoc tools—`get_my_user_info` to confirm its own permissions, then on to booking and managing transports—to get the job done.

Setup guide

Set up Dashdoc 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 Dashdoc 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({
    "dashdoc-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 Dashdoc 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 Dashdoc. 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 Dashdoc 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 Dashdoc MCP in LangChain

First, use the `MultiServerMCPClient` to get the list of Dashdoc tools. Then, pass those tools to a LangChain agent executor, like `create_agent`. The agent will use the tool descriptions to decide which function to call, like using `list_transports` then `get_transport_details`.

Yes, that's what LangChain is built for. You can create a chain where your agent first queries a database for an order number, then passes that number to the Dashdoc `search_transports_by_reference` tool to get the transport details.

Vinkius handles authentication for you. Your MCP endpoint token is all the `MultiServerMCPClient` needs. You don't have to manage API keys or OAuth flows for Dashdoc within your agent's code.

Every call your LangChain agent makes to a Dashdoc tool is automatically traced in LangSmith. You'll see the exact inputs, the raw outputs from tools like `list_fleet_drivers`, and the latency for each step. This makes debugging your agent's reasoning much simpler.

Yes. Your agent's requests to the Dashdoc MCP server are processed in an ephemeral, sandboxed environment on Vinkius. All data in transit, like driver lists or transport order details, is encrypted. The environment is destroyed after your request is complete.

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