How to Use the Hub Planner MCP in LangChain

Q: Can I build a LangChain agent that finds unassigned work in Hub Planner?

Yes, that's a perfect use case. Your agent can use the listunassigned tool to get a list of open bookings. Then, it can chain that with listresources and listtags to find the best person for the job based on skills and availability.

Q: Is it possible to combine multiple MCP servers with the Hub Planner server?

Yes. The MultiServerMCPClient in the LangChain adapter is designed for this. You can register the Hub Planner server alongside others, and the agent will get a unified list of tools to work with from all connected sources.

Build resource planning agents in LangChain by chaining Hub Planner API calls for projects, bookings, and staff availability.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hub Planner MCP to LangChain

Create your Vinkius account to connect Hub Planner 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 Hub Planner with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Hub Planner Tools Together

Give your LangChain agent a goal, not just a command. It can figure out the steps on its own by chaining tools from this MCP server. For example, to staff a new project, an agent can first call `list_projects` to get the project ID, then use `list_resources` to find people with the right tags, and finally check their availability with `list_bookings`. This isn't just a sequence of calls. The output of one tool becomes the input for the next. The agent uses the results from `list_teams` to decide which resources to query next. You build the reasoning chain, and the agent executes it against live Hub Planner data, adapting as it goes.

Build Resource-Aware ReAct Agents

Go beyond simple chains with agents that reason about your resources. A ReAct agent can handle vague requests like, "Who from the London office is on vacation next month?" The agent knows it needs to first find the right team with `list_teams`, then check their schedules using `list_events`. With LangSmith, you get full visibility into the agent's thought process. You can see exactly why it chose to call `list_unassigned` after failing to find a match with `list_bookings`. It makes debugging complex scheduling logic straightforward because every decision is logged.

Connect Planning Data to Other Systems

Your Hub Planner data doesn't have to live in a silo. Since LangChain has hundreds of integrations, you can build agents that combine Hub Planner tools with other APIs. Pull a list of clients with `list_clients`, then fetch their latest payment status from a Stripe tool in the same chain. This lets you create powerful internal tools. For instance, an agent could check for new projects in Hub Planner with `list_projects`, create a corresponding channel in Slack, and then post the project brief from a Notion document. It all happens in one autonomous run.

Setup guide

Set up Hub Planner 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 Hub Planner 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({
    "hub-planner-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 Hub Planner 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 Hub Planner. 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 Hub Planner 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 Hub Planner MCP in LangChain

First, install the adapter with pip. Then, you'll instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL. Call `client.get_tools()` and pass the resulting list directly to your LangChain agent constructor.

Yes, that's a perfect use case. Your agent can use the `list_unassigned` tool to get a list of open bookings. Then, it can chain that with `list_resources` and `list_tags` to find the best person for the job based on skills and availability.

LangChain's agent executors have built-in error handling. If a tool call like `list_projects` fails, the agent can catch the error and decide to retry, call a different tool, or ask the user for help. You can see all of this happening in your LangSmith traces.

Yes. The `MultiServerMCPClient` in the LangChain adapter is designed for this. You can register the Hub Planner server alongside others, and the agent will get a unified list of tools to work with from all connected sources.

This server only accesses data your API key is permissioned for. This includes project details, client lists, resource schedules, team rosters, and booking information. Your Vinkius endpoint token secures the connection, and no data is stored by Vinkius.

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