How to Use the Mashvisor MCP in LlamaIndex

Q: How do I index Mashvisor data using the LlamaIndex MCP adapter?

You install llama-index-tools-mcp and wrap the Vinkius endpoint in a BasicMCPClient to expose Mashvisor tools to LlamaIndex. Once connected, the tool outputs from Mashvisor's getproperty can be converted into document objects and indexed into your LlamaIndex vector store.

Q: Can LlamaIndex search through historical Mashvisor performance records?

Yes, your LlamaIndex agent can call gethistoricalperformance to fetch historical Mashvisor Airbnb data, index that raw JSON, and then perform semantic searches to identify seasonal occupancy trends.

Q: Does this LlamaIndex integration support the Mashvisor investment analysis tool?

Yes, the Mashvisor getinvestmentanalysis tool is fully exposed to LlamaIndex. The LlamaIndex agent can call it to retrieve cash-on-cash return metrics and immediately index those results for future comparison.

Q: How do I limit which Mashvisor tools LlamaIndex can access using MCP?

You can use the allowedtools filter when initializing your LlamaIndex McpToolSpec to restrict access to Mashvisor tools. This lets you restrict your LlamaIndex agent to only read-only Mashvisor tools like getrentalrates if you want to prevent it from browsing active listings.

Index live Mashvisor rental metrics directly into LlamaIndex to query real estate data without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mashvisor MCP to LlamaIndex

Create your Vinkius account to connect Mashvisor 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 Mashvisor with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable Mashvisor real estate knowledge base

LlamaIndex excels at turning active Mashvisor API outputs into searchable data structures. When your LlamaIndex agent calls `get_airbnb_property` or `get_property`, LlamaIndex indexes those detailed Mashvisor sheets directly into your vector database. This means you can query your past Mashvisor property research semantically, asking your LlamaIndex agent to find homes with similar layouts or historical returns. Instead of running redundant Mashvisor API calls, your LlamaIndex agent searches your indexed history first. If it needs fresh Mashvisor data, it uses `get_rental_rates` to update the LlamaIndex index with current traditional lease estimates. You get a self-updating, local LlamaIndex knowledge base of the Mashvisor markets you care about most.

Ground LlamaIndex analysis in live Mashvisor data

Stop letting your LlamaIndex AI guess rental yields or Mashvisor occupancy rates. By connecting this MCP Server to LlamaIndex, your agent grounds its answers in live Mashvisor data retrieved through `get_historical_performance`. Every Mashvisor investment report your LlamaIndex agent generates is backed by actual, verifiable numbers rather than training data. If you ask LlamaIndex about seasonal trends in a specific city, it pulls the historical Mashvisor stats using `get_city_listings` and injects them into the LLM context window. This ensures that your LlamaIndex investment decisions are based on current Mashvisor market realities, protecting you from costly analytical errors.

Query Mashvisor neighborhood metrics with LlamaIndex agents

Use LlamaIndex's `FunctionAgent` to dynamically explore new Mashvisor investment territories. The LlamaIndex agent can scan a broad region using `list_neighborhoods` to identify areas where short-term Mashvisor rental yields outpace traditional leases. It automatically extracts the relevant Mashvisor metrics and formats them into clean LlamaIndex data frames for your review. You can configure the LlamaIndex `McpToolSpec` to include underlying Mashvisor data resources, giving your agent direct access to raw property schemas. This allows your LlamaIndex agent to perform deep mathematical calculations on the numbers returned by Mashvisor's `get_investment_analysis` without losing fidelity.

Setup guide

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

You install `llama-index-tools-mcp` and wrap the Vinkius endpoint in a `BasicMCPClient` to expose Mashvisor tools to LlamaIndex. Once connected, the tool outputs from Mashvisor's `get_property` can be converted into document objects and indexed into your LlamaIndex vector store.

Yes, your LlamaIndex agent can call `get_historical_performance` to fetch historical Mashvisor Airbnb data, index that raw JSON, and then perform semantic searches to identify seasonal occupancy trends.

Yes, the Mashvisor `get_investment_analysis` tool is fully exposed to LlamaIndex. The LlamaIndex agent can call it to retrieve cash-on-cash return metrics and immediately index those results for future comparison.

You can use the `allowed_tools` filter when initializing your LlamaIndex `McpToolSpec` to restrict access to Mashvisor tools. This lets you restrict your LlamaIndex agent to only read-only Mashvisor tools like `get_rental_rates` if you want to prevent it from browsing active listings.

Vinkius executes the Mashvisor MCP Server in a secure, ephemeral V8 isolate that isolates your property search parameters and LlamaIndex API tokens. No Mashvisor real estate query data or rental rate requests are stored on Vinkius servers, ensuring complete operational privacy.

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