How to Use the Howspace MCP in LlamaIndex

Q: How can I use LlamaIndex to search for participants across all my Howspace workspaces?

You'd create a LlamaIndex agent that periodically calls listworkspaces and listparticipants, indexing the results. Then you can query that index with natural language to find people, and the agent will synthesize an answer from the data it collected.

Q: How to connect LlamaIndex to Howspace to get workspace details?

You use the McpToolSpec from the LlamaIndex tools library, passing it your Vinkius MCP endpoint. This exposes all the Howspace tools, including getworkspace, to your LlamaIndex agent.

Q: What data is stored when LlamaIndex indexes my Howspace participant lists?

When your agent calls listparticipants, LlamaIndex will process and store participant metadata like names and emails in your chosen vector database. The connection itself is stateless and secured by the Vinkius MCP runtime.

Build RAG apps over your live Howspace data. Let LlamaIndex turn your workshop activity into a queryable knowledge base.

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 LlamaIndex

Create your Vinkius account to connect Howspace to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Howspace Activity

LlamaIndex doesn't just call the Howspace API; it remembers the answers. You can set up an agent to run `list_workspaces` and `list_participants` on a schedule, then index the results into a vector store. This creates a searchable history of your organizational development work. Now your agent can answer questions about past activity without hitting the live API every single time. Your operational data becomes a source for real insights.

Query Workspaces with Natural Language

Ask questions in plain English, and get answers grounded in facts. "Show me all participants in the 'Q4 Onboarding' workspace." LlamaIndex finds the relevant text it indexed from the `list_participants` tool and gives you a direct answer. This is Retrieval-Augmented Generation at its best. Your agent grounds its answers in the actual data it indexed from Howspace tools like `get_workspace`. You get facts from your own instance, not hallucinations.

Build a Knowledgeable LlamaIndex Agent

The real advantage is mixing data sources. Your LlamaIndex agent can pull a list of new hires from a Workday export, find their assigned training cohort in a Google Sheet, and then use the `add_participant` tool to enroll them in the right Howspace session. LlamaIndex unifies these different sources into one queryable index. It can see a campaign name in a Confluence doc, find the matching ID with `list_campaigns` from this MCP server, and then use `list_workspaces` to show you all related activities.

Setup guide

Set up Howspace MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Howspace MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Howspace tools.",
)
response = await agent.run("List recent Howspace data")

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 LlamaIndex

You'd create a LlamaIndex agent that periodically calls `list_workspaces` and `list_participants`, indexing the results. Then you can query that index with natural language to find people, and the agent will synthesize an answer from the data it collected.

Yes, that's its primary function. By indexing the output of tools like `list_campaigns` and `get_workspace`, LlamaIndex creates a vector index that your AI client can query to get information about your Howspace setup.

You use the `McpToolSpec` from the LlamaIndex tools library, passing it your Vinkius MCP endpoint. This exposes all the Howspace tools, including `get_workspace`, to your LlamaIndex agent.

No. Your Vinkius endpoint token is all you need. Vinkius manages the underlying Howspace API credentials and authentication for you, so your agent's connection is simple and secure.

When your agent calls `list_participants`, LlamaIndex will process and store participant metadata like names and emails in your chosen vector database. The connection itself is stateless and secured by the Vinkius MCP runtime.

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