How to Use the Ghostfolio (Investment Tracker) MCP in LlamaIndex

Q: Can I index my Ghostfolio (Investment Tracker) transaction history?

Yes. You pull your records using the listactivities tool and embed the JSON responses directly into your LlamaIndex vector store for semantic search.

Q: Will LlamaIndex hallucinate my Ghostfolio (Investment Tracker) portfolio value?

No. By forcing the agent to call getportfoliosummary before answering, the framework grounds its response in your actual live data.

Q: Can I restrict which tools the agent can access?

You can use the allowedtools filter when setting up the MCP tool spec. This lets you expose read-only tools while hiding write operations like deleteactivity.

Index your Ghostfolio wealth data into LlamaIndex to build searchable, RAG-powered financial knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ghostfolio (Investment Tracker) MCP to LlamaIndex

Create your Vinkius account to connect Ghostfolio (Investment Tracker) 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 Ghostfolio (Investment Tracker) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn holdings into a searchable LlamaIndex RAG

This MCP Server lets your LlamaIndex application pull live investment data and index it alongside your documents. You run `get_portfolio_holdings` to grab your current asset allocation and valuations. The framework then chunks and embeds that data right into your vector store. Now your financial reality is queryable. You can ask your RAG application why your tech allocation dropped, and it cross-references your live Ghostfolio data against the market reports you already indexed. It grounds every answer in actual API data, killing hallucinations instantly.

Track performance history and activities

You need to know what happened and when. Your application can fire `list_activities` to pull every buy, sell, and dividend event. Pass that through `get_portfolio_summary` to capture the high-level performance metrics, then index the results. This turns a static dashboard into a conversational financial analyst. You query past sessions or configurations, and LlamaIndex retrieves the exact transaction history that caused a spike in your net worth. You stop digging through charts and start asking direct questions.

Manage accounts and market data context

The integration handles write operations just as easily. Use `create_account` to set up a new tracking silo, or `update_account` to adjust its parameters. Your agent keeps the structural data accurate while you focus on analysis. When you need immediate context, your FunctionAgent can call `get_market_data_price` for specific symbols. It pulls the live price, injects it into the current query context, and gives you an answer based on what the market is doing right this second. It is a massive upgrade over static knowledge bases.

Setup guide

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

Install llama-index-tools-mcp. Set up a BasicMCPClient with your URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Yes. You pull your records using the list_activities tool and embed the JSON responses directly into your LlamaIndex vector store for semantic search.

No. By forcing the agent to call get_portfolio_summary before answering, the framework grounds its response in your actual live data.

You can use the allowed_tools filter when setting up the MCP tool spec. This lets you expose read-only tools while hiding write operations like delete_activity.

LlamaIndex only processes the specific asset valuations, ticker symbols, and transaction histories you explicitly query. The MCP Server runs in an isolated sandbox, ensuring your private wealth metrics never leak into unauthorized indexes or public model training sets.

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