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

Chain Ghostfolio investment data directly into your LangChain agents to build automated wealth tracking and portfolio analysis pipelines.

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 LangChain

Create your Vinkius account to connect Ghostfolio (Investment Tracker) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build autonomous LangChain wealth agents

This MCP Server connects your ReAct agents directly to your investment data. You give the agent a goal like "audit my recent trades," and it figures out the rest. It calls `list_activities` to pull your raw transaction logs, then feeds that context into its reasoning loop. The real power is chaining these operations together. Your agent can pull performance metrics with `get_portfolio_summary`, realize it needs more detail, and automatically follow up with `get_portfolio_holdings` to isolate the underperforming assets. You get a complete, traceable pipeline in LangSmith.

Execute trades and manage accounts

Stop manually entering data into spreadsheets. You can wire your LangChain application to parse emails or broker statements and automatically fire `create_activity` to log the buy or sell event in Ghostfolio. If an entry looks wrong, your agent can catch the anomaly and trigger `delete_activity` to roll it back. Account management works the exact same way. Use `create_account` to spin up a new tracking bucket for a specific asset class, then keep it synced. The agent handles the tedious data entry while you focus on the actual strategy.

Inject real-time market pricing

A portfolio is useless without current valuations. Your chains can hit `get_market_data_price` to pull the latest ticker prices mid-execution. Combine this with your existing LangChain vector stores to cross-reference current market realities against your historical performance. Because this is an MCP integration, you never write custom API wrappers. You just pass the tools to your multi-step reasoning pipeline. The agent decides when it needs fresh pricing data, grabs it, and continues generating your financial report.

Setup guide

Set up Ghostfolio (Investment Tracker) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Ghostfolio (Investment Tracker) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ghostfolio-investment-tracker-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Ghostfolio (Investment Tracker) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use the MultiServerMCPClient and pass your endpoint URL. Call client.get_tools() and hand the array directly to your create_agent function.

Yes. Your agent can parse text or documents and use the create_activity tool to record the transaction. You control the logic and validation steps.

You can build human-in-the-loop approval steps in LangGraph before the agent executes write operations like update_account. This prevents unauthorized database modifications.

You bet. You can load this MCP Server alongside your database tools. The agent will route requests to the correct server based on the task.

Your LangChain client only reads the specific account details, transaction logs, and holdings you request. The MCP architecture isolates the execution, meaning your wealth data stays between your self-hosted server and your local agent memory.

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