How to Use the Howspace MCP in LangChain

Q: How to create a Howspace workspace with a LangChain agent?

You build a chain or agent that calls the createworkspace tool. The agent can prompt you for a name or get it from another source, then execute the tool to provision the new Howspace session.

Q: What's the best way to list all Howspace participants for a campaign using LangChain?

Create a two-step chain. The first tool, listworkspaces, gets all workspaces for a given campaign. The second tool, listparticipants, then runs on each of those workspace IDs to collect all the user lists.

Build custom LangChain agents that manage your Howspace workshops, from creation to participant invites.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Howspace MCP to LangChain

Create your Vinkius account to connect Howspace 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 Howspace with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Workshop Provisioning

Stop creating workshops by hand. Build a LangChain agent that takes a simple prompt, like "Create a Q4 leadership offsite," and turns it into a real, ready-to-use workspace. Your agent can chain together the tools. First, it finds the right initiative using `list_campaigns`. Then it calls `create_workspace` to spin up the session. Finally, it can pull a list from a database or a file and use `add_participant` to invite everyone automatically. You just give the order.

Chain Together Howspace MCP Server Tools

LangChain treats each Howspace tool as a link in a chain. This means the output of one tool becomes the input for the next. It’s how you build multi-step logic without writing a bunch of glue code. For example, create a simple chain to generate attendance reports. The first step calls `list_workspaces` to find a specific session. The next step takes that workspace ID and feeds it to `list_participants`. Because it's a chain, every call is traced, so you can see exactly what your agent did and why.

Build a Custom Admin Bot

Build an agent that acts as a junior L&D assistant. Ask it to "check on the new sales onboarding program," and it can figure out how to chain `list_campaigns` with `list_workspaces` to give you a status report. This isn't just about running one tool at a time. This is about giving a ReAct agent a goal and letting it decide the sequence of `get_workspace` and `list_participants` calls needed to get you an answer. It's a real assistant that can reason about your Howspace setup.

Setup guide

Set up Howspace 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 Howspace 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({
    "howspace-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 Howspace 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 Howspace. 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 Howspace 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 Howspace MCP in LangChain

You build a chain or agent that calls the `create_workspace` tool. The agent can prompt you for a name or get it from another source, then execute the tool to provision the new Howspace session.

Yes. You can design a chain that iterates through a list of user emails and workspace IDs. In each loop, it calls the `add_participant` tool to enroll the user in the corresponding Howspace workspace.

Create a two-step chain. The first tool, `list_workspaces`, gets all workspaces for a given campaign. The second tool, `list_participants`, then runs on each of those workspace IDs to collect all the user lists.

It's handled for you by the Vinkius platform. You get a single endpoint token that you provide to the LangChain MCP client, which secures the connection to your Howspace instance.

The agent only accesses the data your tools ask for. If your chain calls `list_participants`, it will handle participant names and emails from Howspace. Vinkius secures this data in-transit within an ephemeral, zero-trust sandbox.

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