How to Use the Hub Planner MCP in LlamaIndex

Q: How do I connect LlamaIndex to my Hub Planner account?

You'll use the llama-index-tools-mcp library. Instantiate the BasicMCPClient with your Vinkius URL, then wrap it with McpToolSpec. From there, you can generate a tool list to pass to your LlamaIndex agent.

Q: Can I use LlamaIndex to ask questions about my Hub Planner resources?

Absolutely. You can use the listresources and listtags tools to fetch all your staff and their skills, then index that data. This lets you build a RAG application where you can ask things like, "Find me a Python developer in the New York office."

Ground your LlamaIndex RAG apps in live Hub Planner data. Query project status, resource schedules, and client lists with natural language.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Hub Planner Data

Turn your Hub Planner account into a searchable knowledge base. Use the tools in this MCP server to fetch and index your operational data. Run `list_resources`, `list_projects`, and `list_teams` to create a vector index of who does what and where. Once indexed, you can ask complex questions in natural language, like "Show me all active projects for our top three clients" or "Who are the available designers with Figma experience?" LlamaIndex finds the answer from the data you've already indexed, giving you fast, accurate responses without constant API calls.

Augment Queries with Live Data

Combine indexed knowledge with real-time information. A LlamaIndex agent can first search its existing index for relevant projects, then call `list_bookings` to get the absolute latest schedule for the resources involved. This hybrid approach gives you the speed of a local index with the accuracy of a live API call. This is great for building Q&A bots about your agency's operations. A project manager could ask, "What's the status of the Apollo project and is anyone blocked?" The agent can pull the project summary from the index and then use `list_events` to check for any last-minute time off that might cause a delay.

Build a Custom Hub Planner Tool Spec

You have full control over which tools your LlamaIndex agent can access. After creating the client, you can use `McpToolSpec` to generate a list of tools. You can easily filter this list to create specialized agents, like a "Scheduler" agent that can only access `list_bookings` and `list_unassigned`. This lets you build safer, more focused applications. For a client-facing RAG app, you might expose `list_projects` but hide `list_clients` and financial data. You get the power of an MCP server with the granular control needed for production systems.

Setup guide

Set up Hub Planner 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 Hub Planner 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 Hub Planner tools.",
)
response = await agent.run("List recent Hub Planner 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 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 LlamaIndex

You'll use the `llama-index-tools-mcp` library. Instantiate the `BasicMCPClient` with your Vinkius URL, then wrap it with `McpToolSpec`. From there, you can generate a tool list to pass to your LlamaIndex agent.

Absolutely. You can use the `list_resources` and `list_tags` tools to fetch all your staff and their skills, then index that data. This lets you build a RAG application where you can ask things like, "Find me a Python developer in the New York office."

You can set up a simple script to periodically run the MCP tools—like `list_projects` and `list_bookings`—and re-index the results. For many use cases, running this once a day is enough to keep your knowledge base fresh.

Yes, that's the core of how LlamaIndex agents work. The agent understands the description of each tool and can decide that for time-sensitive questions, it's better to call `list_bookings` directly instead of relying on a potentially stale index.

The server can access details about your projects, resources, clients, teams, and their schedules. Your API key's permissions dictate what's available. The connection is encrypted, and Vinkius processes requests ephemerally without retaining any of your Hub Planner data.

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