How to Use the Planhat MCP in LlamaIndex

Q: How do I index Planhat company data into LlamaIndex?

You fetch company details using listplanhatcompanies and load the resulting JSON into LlamaIndex Document objects. From there, you build a vector index that allows your agent to run semantic searches over your entire Planhat account list.

Q: Can LlamaIndex query Planhat tasks to find overdue items?

Yes, you can use listplanhattasks to pull the active task list and index it for your LlamaIndex agent. The agent can then search for specific assignees or overdue dates using natural language queries instead of writing SQL.

Q: How does LlamaIndex handle Planhat licenses via MCP?

The listplanhatlicenses tool is converted into a structured LlamaIndex tool that your agent can invoke dynamically. When a query requires license verification, the agent automatically triggers the tool and parses the active seat count.

Index live Planhat MCP data into LlamaIndex to query customer health and tasks using semantic RAG search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Planhat MCP to LlamaIndex

Create your Vinkius account to connect Planhat to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Planhat with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Planhat MCP Server metadata for semantic search

`list_planhat_end_users` provides the raw user profiles that LlamaIndex parses and indexes into your vector database. Instead of searching by exact matching IDs, you can query your customer base using natural language to find active users. This index-driven approach connects your live customer records to your local RAG pipelines. By combining `list_planhat_companies` with your vector store, your LlamaIndex agent answers complex questions about account distribution without manual database queries.

Ground RAG answers in real-time Planhat assets

`list_planhat_assets` exposes the physical or digital assets assigned to each account, which LlamaIndex uses to ground its answers. Your query engine reads these live assets to ensure it never hallucinates what a customer actually owns. Stale data is eliminated when you ground queries this way. When a user asks about a customer's active deployment, LlamaIndex pulls the latest records using this MCP tool, guaranteeing the response matches what is currently live in Planhat.

Build a queryable history of customer conversations

`list_planhat_conversations` retrieves historical support threads and chat logs, allowing LlamaIndex to index past customer interactions for semantic search. You can ask your agent for the general sentiment of recent chats, and it will pull the relevant logs to synthesize a precise summary. Combining this with `list_planhat_notes` gives your support team a unified search bar for all qualitative data. LlamaIndex searches across both endpoints to find patterns in customer complaints or feature requests.

Setup guide

Set up Planhat 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 Planhat 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 Planhat tools.",
)
response = await agent.run("List recent Planhat 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 Planhat. 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 Planhat 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 Planhat MCP in LlamaIndex

You fetch company details using `list_planhat_companies` and load the resulting JSON into LlamaIndex Document objects. From there, you build a vector index that allows your agent to run semantic searches over your entire Planhat account list.

Yes, you can use `list_planhat_tasks` to pull the active task list and index it for your LlamaIndex agent. The agent can then search for specific assignees or overdue dates using natural language queries instead of writing SQL.

The `list_planhat_licenses` tool is converted into a structured LlamaIndex tool that your agent can invoke dynamically. When a query requires license verification, the agent automatically triggers the tool and parses the active seat count.

Yes, you can pass an allowed tools list to your LlamaIndex agent setup to limit access. For example, you can expose only `get_planhat_company` while keeping sensitive billing tools hidden from the query engine.

Vinkius runs the MCP server in an ephemeral container, ensuring your Planhat license keys, end-user emails, and company notes are never saved to disk. All data transfers happen over encrypted channels directly between your LlamaIndex client and the secure 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