Ghostfolio MCP

Ghostfolio MCP Server

Ghostfolio MCP Server is a Python-based Model Context Protocol (MCP) server designed to provide advanced, programmable access to Ghostfolio portfolio management and financial data. It exposes a modern API for querying, analyzing, and managing your investment portfolio through Ghostfolio's comprehensive features. The server supports both read and write operations, robust security features, and is suitable for integration with automation tools, financial dashboards, and custom portfolio management applications.

Features

Core Features

• Query portfolio performance, holdings, and positions with flexible time ranges
• Retrieve comprehensive investment data including dividends, returns, and allocations
• Access detailed market data, asset profiles, and historical price information
• Monitor portfolio metrics, benchmarks, and performance comparisons
• Track orders, transactions, and account balances across multiple accounts
• Search and lookup financial symbols, stocks, ETFs, and other assets
• Get user information, settings, and account details

Management Operations

• Create and manage investment accounts with different currencies and platforms
• Create, delete, and manage individual transactions and activities
• Import transactions and historical data from other platforms
• Configure read-only mode to restrict all write operations for safe monitoring
• Support for bulk transaction imports and portfolio data management
• Monitor system health and platform availability

Advanced Capabilities

• Rate limiting and API security features
• Real-time portfolio monitoring and performance tracking
• Comprehensive logging and audit trails
• SSL/TLS support and configurable timeouts
• Extensible with custom middlewares and tag-based tool filtering
• Optional tool-search transform for large tool catalogs
• Bearer token or OIDC/OAuth authentication for HTTP transports

Installation

Prerequisites

• Python 3.11 to 3.15
• Access to a Ghostfolio instance
• Valid Ghostfolio API token

Quick Install from PyPI

The easiest way to get started is to install from PyPI:

# Using UV (recommended)
uvx ghostfolio-mcp

# Or using pip
pip install ghostfolio-mcp

Remember to configure the environment variables for your Ghostfolio instance before running the server:

# Create environment configuration
export GHOSTFOLIO_URL=https://domain.tld:3333
export GHOSTFOLIO_TOKEN=your-ghostfolio-token

For more details, visit: https://pypi.org/project/ghostfolio-mcp/

Install from Source

1. Clone the repository:

git clone https://github.com/mhajder/ghostfolio-mcp.git
cd ghostfolio-mcp

2. Install dependencies:

# Using UV (recommended)
uv sync

# Or using pip
pip install -e .

3. Configure environment variables:

cp .env.example .env
# Edit .env with your Ghostfolio URL and token

4. Run the server:

# Using UV (recommended)
uv run ghostfolio-mcp

# Or using the installed command directly
ghostfolio-mcp

Development Setup

For development with additional tools:

# Clone and install with development dependencies
git clone https://github.com/mhajder/ghostfolio-mcp.git
cd ghostfolio-mcp
uv sync --group dev

# Run tests
uv run pytest

# Run with coverage
uv run pytest --cov=src/

# Run linting and formatting
uv run ruff check .
uv run ruff format .

# Run type checking
uv run ty check .

# Setup prek hooks
uv run prek install

Configuration

Environment Variables

A blank or whitespace-only value counts as unset and uses the default. Boolean settings accept true/false, 1/0, yes/no and on/off (any case). Any other value stops the server at startup, so a typo cannot silently turn read-only mode or TLS verification off.

# Ghostfolio Connection Details
GHOSTFOLIO_URL=https://domain.tld:3333
GHOSTFOLIO_TOKEN=your-ghostfolio-token

# SSL Configuration
GHOSTFOLIO_VERIFY_SSL=true
GHOSTFOLIO_TIMEOUT=30

# Read-Only Mode
# Set READ_ONLY_MODE true to disable all write operations (put, post, delete)
READ_ONLY_MODE=false

# Disabled Tags
# Comma-separated list of tags to disable tools for (empty by default)
# Example: GHOSTFOLIO_DISABLED_TAGS=portfolio,symbol
GHOSTFOLIO_DISABLED_TAGS=

# Logging Configuration
LOG_LEVEL=INFO

# Rate Limiting (requests per minute)
# Set RATE_LIMIT_ENABLED true to enable rate limiting
RATE_LIMIT_ENABLED=false
RATE_LIMIT_MAX_REQUESTS=60
RATE_LIMIT_WINDOW_MINUTES=1

# Tool Search Transform (Optional)
# Set TOOL_SEARCH_ENABLED true to replace full tool listings with search_tools + call_tool
TOOL_SEARCH_ENABLED=false
# Search strategy: bm25 (natural language) or regex (pattern match)
TOOL_SEARCH_STRATEGY=bm25
# Maximum number of tools returned by search_tools
TOOL_SEARCH_MAX_RESULTS=5

# Sentry Error Tracking (Optional)
# Set SENTRY_DSN to enable error tracking and performance monitoring
# SENTRY_DSN=https://your-key@o12345.ingest.us.sentry.io/6789
# Optional Sentry configuration
# SENTRY_TRACES_SAMPLE_RATE=1.0
# SENTRY_SEND_DEFAULT_PII=false
# SENTRY_ENVIRONMENT=production
# SENTRY_RELEASE=1.2.3
# SENTRY_PROFILE_SESSION_SAMPLE_RATE=1.0
# SENTRY_PROFILE_LIFECYCLE=trace
# SENTRY_ENABLE_LOGS=true

# MCP Transport Configuration
# Transport type: 'stdio' (default), 'sse' (Server-Sent Events), or 'http' (HTTP Streamable)
# 'streamable-http' is accepted as an alias for 'http'. Any other value stops
# the server at startup.
MCP_TRANSPORT=stdio

# HTTP Transport Settings (used when MCP_TRANSPORT=sse or MCP_TRANSPORT=http)
# Host to bind the HTTP server (default: 127.0.0.1)
# MCP_HTTP_HOST=127.0.0.1
# Port to bind the HTTP server (default: 8000)
# MCP_HTTP_PORT=8000
# Optional bearer token for authentication (leave empty for no auth)
# MCP_HTTP_BEARER_TOKEN=

# OIDC / OAuth Authentication (optional, for remote hosting)
# Set all four to enable; takes precedence over MCP_HTTP_BEARER_TOKEN
# OIDC_CONFIG_URL=https://id.example.com/.well-known/openid-configuration
# OIDC_CLIENT_ID=
# OIDC_CLIENT_SECRET=
# OIDC_BASE_URL=https://ghostfolio-mcp.example.com
# Optional OIDC settings
# OIDC_REDIRECT_PATH=/auth/callback
# OIDC_REQUIRED_SCOPES=
# OIDC_ALLOWED_REDIRECT_URIS=
# OIDC_VERIFY_ID_TOKEN=false
# OIDC_FORWARD_RESOURCE=false

Sentry Error Tracking & Monitoring (Optional)

The server optionally supports Sentry for error tracking, performance monitoring, and debugging. Sentry integration is completely optional and only initialized if configured.

Installation

To enable Sentry monitoring, install the optional dependency:

# Using UV (recommended)
uv sync --extra sentry

Configuration

Enable Sentry by setting the SENTRY_DSN environment variable in your .env file:

# Required: Sentry DSN for your project
SENTRY_DSN=https://your-key@o12345.ingest.us.sentry.io/6789

# Optional: Performance monitoring sample rate (0.0-1.0, default: 1.0)
SENTRY_TRACES_SAMPLE_RATE=1.0

# Optional: Include personally identifiable information (default: false).
# When true, tool inputs and outputs (portfolio data) are sent to Sentry.
SENTRY_SEND_DEFAULT_PII=false

# Optional: Environment name (e.g., "production", "staging")
SENTRY_ENVIRONMENT=production

# Optional: Release version (auto-detected from package if not set)
SENTRY_RELEASE=1.2.2

# Optional: Profiling - continuous profiling sample rate (0.0-1.0, default: 1.0)
SENTRY_PROFILE_SESSION_SAMPLE_RATE=1.0

# Optional: Profiling - lifecycle mode for profiling (default: "trace")
# Options: "all", "continuation", "trace"
SENTRY_PROFILE_LIFECYCLE=trace

# Optional: Enable log capture as breadcrumbs and events (default: true)
SENTRY_ENABLE_LOGS=true

Features

When enabled, Sentry automatically captures:

• Exceptions & Errors: All unhandled exceptions with full context
• Performance Metrics: Request/response times and traces
• MCP Integration: Detailed MCP server activity and interactions
• Logs & Breadcrumbs: Application logs and event trails for debugging
• Context Data: Environment, client info, and request parameters

Getting a Sentry DSN

1. Create a free account at sentry.io
2. Create a new Python project
3. Copy your DSN from the project settings
4. Set it in your .env file

Disabling Sentry

Sentry is completely optional. If you don't set SENTRY_DSN, the server will run normally without any Sentry integration, and no monitoring data will be collected.

Available Tools

Account Management Tools

• get_accounts: Get all accounts in your portfolio including account types and balances
• get_account_balances: Get account balances for a specific account
• create_account: Create a new account in your portfolio
• delete_account: Delete an existing account from your portfolio (destructive operation)
• get_account_details: Get details for a specific account
• update_account: Update settings or details of an existing account
• transfer_account_balance: Transfer cash balances between two accounts
• create_account_balance: Set an account's balance for a specific date in its balance history (defaults to today)
• delete_account_balance: Delete a single entry from an account's balance history

Portfolio & Transaction Management Tools

• get_portfolio_performance: Get portfolio performance data including returns, benchmarks, and performance metrics
• get_portfolio_holdings: Get portfolio holdings and positions including allocations and asset breakdowns
• get_portfolio_details: Get comprehensive portfolio details including accounts, positions, and summary
• get_position: Get position details for a specific symbol from a data source
• get_investments: Get investment data grouped by time period showing cash flows and contributions
• get_dividends: Get dividend data grouped by time period showing dividend payments and yield
• get_orders: Get all activities/orders from your portfolio, optionally filtered by account
• create_activity: Create a single new transaction/activity in your portfolio (BUY, SELL, DIVIDEND, INTEREST, FEE, etc.), optionally with tags
• update_activity: Update an existing activity/transaction, including its tags; fields you don't pass keep their current values
• delete_activity: Delete a single activity/transaction by its ID (destructive operation)

Benchmark Tools

• get_benchmarks: Get all configured benchmarks
• get_benchmark_performance: Compare portfolio performance against a benchmark symbol starting from a specific date

Watchlist Tools

• get_watchlist: Get all items in the user's watchlist
• add_to_watchlist: Add a symbol to the user's watchlist
• remove_from_watchlist: Remove a symbol from the user's watchlist

Exchange Rate Tools

• get_exchange_rate: Get the exchange rate for a given currency symbol on a specific date

Data Export Tools

• export_portfolio: Export portfolio activities/transactions data as JSON

Market Data & Symbol Tools

• get_market_data_for_asset: Get market data for a specific asset
• add_market_data_points: Add one or more market data points for an asset (typically a MANUAL data source — Ghostfolio rejects writes for auto-fetched sources)
• get_symbol_data: Get symbol data for a specific asset from a data source
• get_historical_data: Get historical data for a specific symbol on a specific date
• lookup_symbols: Search for symbols using a query string
• get_asset_profile: Get asset profile information for a specific symbol
• upsert_asset_profile: Create-or-update an asset profile, including optional countries and sectors allocations (idempotent; tolerates Ghostfolio's HTTP 500 on the create step and relies on the subsequent PATCH as the source of truth)
• delete_asset_profile: Delete an asset profile (destructive operation; may delete associated activities and market data depending on backend rules)

Data Import Tools

• import_transactions: Import transactions into your portfolio (bulk import operation)
• get_dividends_for_import: Fetch historical dividend data formatted for import for a specific symbol

System & Platform Tools

• get_health: Get system health status of the Ghostfolio backend service
• get_platforms: Get list of available platforms (brokers, exchanges, etc.) for account tracking

User Management Tools

• get_user_info: Get user information and settings

Security & Safety Features

Read-Only Mode

The server supports a read-only mode that disables all write operations for safe monitoring:

READ_ONLY_MODE=true

When enabled, this mode prevents any modifications to your portfolio data while still allowing full read access to all information.

Tag-Based Tool Filtering

You can disable specific categories of tools by setting disabled tags:

GHOSTFOLIO_DISABLED_TAGS=portfolio,symbol,import

Available tags include:

• account - Account management tools (create, delete, update, get accounts)
• portfolio - Portfolio analysis and performance tools
• symbol - Symbol lookup and data tools
• import - Data import tools
• asset - Asset profile tools
• user - User information tools
• system - System health and platform information tools
• activities - Activity/transaction management tools (create, update, delete activities)
• watchlist - Watchlist management tools
• exchange-rate - Currency exchange rate tools
• export - Data export tools
• benchmark - Benchmark tools

Rate Limiting

The server supports rate limiting to control API usage and prevent abuse. If enabled, requests are limited per client using a sliding window algorithm.

Enable rate limiting by setting the following environment variables in your .env file:

RATE_LIMIT_ENABLED=true
RATE_LIMIT_MAX_REQUESTS=60    # Maximum requests allowed per window
RATE_LIMIT_WINDOW_MINUTES=1   # Window size in minutes

If RATE_LIMIT_ENABLED is set to true, the server will apply rate limiting middleware. Adjust RATE_LIMIT_MAX_REQUESTS and RATE_LIMIT_WINDOW_MINUTES as needed for your environment. While rate limiting is on, both must be at least 1; while it is off, they are not read.

Tool Search for Large Toolsets

FastMCP tool search can reduce prompt size for servers with many tools. When enabled, list_tools returns two synthetic tools:

• search_tools: Finds matching tools and returns their full schemas
• call_tool: Executes any discovered tool by name

Enable it with:

TOOL_SEARCH_ENABLED=true
TOOL_SEARCH_STRATEGY=bm25      # bm25 or regex
TOOL_SEARCH_MAX_RESULTS=8      # optional, default is 5

bm25 supports natural language queries, while regex uses a regex pattern input for deterministic matching. While tool search is on, any other strategy, or a TOOL_SEARCH_MAX_RESULTS below 1, stops the server at startup; while it is off, these settings are not read.

Tool search respects existing visibility controls (read-only mode and disabled tags).

SSL/TLS Configuration

The server supports SSL certificate verification and custom timeout settings:

GHOSTFOLIO_VERIFY_SSL=true    # Enable SSL certificate verification
GHOSTFOLIO_TIMEOUT=30         # Connection timeout in seconds

Transport Configuration

The server supports multiple transport protocols for different deployment scenarios:

STDIO Transport (Default)

The default transport uses standard input/output for communication. This is ideal for local usage and integration with tools that communicate via stdin/stdout:

MCP_TRANSPORT=stdio

HTTP SSE Transport (Server-Sent Events)

For network-based deployments, you can use HTTP with Server-Sent Events. This allows the MCP server to be accessed over HTTP with real-time streaming:

MCP_TRANSPORT=sse
MCP_HTTP_HOST=127.0.0.1        # Localhost
MCP_HTTP_PORT=8000           # Port to listen on
MCP_HTTP_BEARER_TOKEN=your-secret-token  # Optional authentication token

When using SSE transport with a bearer token, clients must include the token in their requests:

curl -H "Authorization: Bearer your-secret-token" http://localhost:8000/sse

HTTP Streamable Transport

The HTTP Streamable transport provides HTTP-based communication with request/response streaming. This is ideal for web integrations and tools that need HTTP endpoints:

MCP_TRANSPORT=http
MCP_HTTP_HOST=127.0.0.1        # Localhost
MCP_HTTP_PORT=8000           # Port to listen on
MCP_HTTP_BEARER_TOKEN=your-secret-token  # Optional authentication token

When using streamable transport with a bearer token:

curl -H "Authorization: Bearer your-secret-token" \
     -H "Accept: application/json, text/event-stream" \
     -H "Content-Type: application/json" \
     -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \
     http://localhost:8000/mcp

Note: The HTTP transport requires proper JSON-RPC formatting with jsonrpc and id fields. The server may also require session initialization for some operations.

Health Endpoint

Both HTTP transports (sse and http) serve GET /health, which answers 200 ok when the server is handling requests. It needs no bearer token or OIDC login and does not contact Ghostfolio, so a Ghostfolio outage does not mark the MCP server unhealthy. The Docker image's HEALTHCHECK uses it:

curl http://localhost:8000/health

OIDC / OAuth Authentication (Optional)

A static bearer token is enough for machine-to-machine clients, but many MCP clients can only authenticate over OAuth with Dynamic Client Registration. For those, the server can act as an OAuth interface in front of an existing OIDC identity provider (Authentik, Keycloak, PocketID, Auth0, Entra ID, ...) using FastMCP's OIDCProxy. Clients register and authenticate against this server; the server brokers the flow upstream. No Ghostfolio credential ever reaches the client.

This applies to the sse and http transports only.

Registering the client

Create a confidential client (client ID + secret) on your identity provider with the redirect URI set to OIDC_BASE_URL + OIDC_REDIRECT_PATH, for example https://ghostfolio-mcp.example.com/auth/callback.

Configuration

MCP_TRANSPORT=http
MCP_HTTP_HOST=0.0.0.0
MCP_HTTP_PORT=8000

# All four are required to enable OIDC
OIDC_CONFIG_URL=https://id.example.com/.well-known/openid-configuration
OIDC_CLIENT_ID=your-client-id
OIDC_CLIENT_SECRET=your-client-secret
# Public URL where this server is reachable, used to build its OAuth endpoints.
# Must be HTTPS (except on localhost), as required for an OAuth issuer.
OIDC_BASE_URL=https://ghostfolio-mcp.example.com

OIDC is entirely optional. Leaving these unset keeps the existing behaviour, and a partially configured setup is ignored with a warning rather than half-enabled. When OIDC is configured it takes precedence over MCP_HTTP_BEARER_TOKEN.

Optional settings:

# Callback path registered on the identity provider (default: /auth/callback)
OIDC_REDIRECT_PATH=/auth/callback

# Comma-separated scopes required on presented tokens
OIDC_REQUIRED_SCOPES=openid,profile

# Comma-separated allowed client redirect URI patterns (wildcards accepted)
OIDC_ALLOWED_REDIRECT_URIS=https://example.com/*

# Verify the id_token instead of the access token (default: false)
OIDC_VERIFY_ID_TOKEN=false

# Forward the RFC 8707 'resource' indicator upstream (default: false)
OIDC_FORWARD_RESOURCE=false

OIDC_ALLOWED_REDIRECT_URIS restricts which clients may complete the flow. Leaving it unset accepts any redirect URI a client registers, so set it to the hosts you expect, for example https://example.com/*.

Set OIDC_VERIFY_ID_TOKEN=true if your identity provider issues opaque (non-JWT) access tokens; the id_token is then verified instead.

OIDC_FORWARD_RESOURCE is off by default because identity providers that do not implement RFC 8707 resource indicators reject the authorization request with invalid_request, which breaks login immediately after consent. Turn it on only if your provider supports resource indicators. Token audience binding is unaffected either way.

Persisting OAuth state

Client registrations and encrypted tokens are stored on disk, under FastMCP's data directory. If that directory is not persistent, every restart forces all clients to register and authenticate again. The Docker image sets FASTMCP_HOME=/data, so mount a volume there:

docker run -v ghostfolio-mcp-data:/data --env-file .env ghcr.io/mhajder/ghostfolio-mcp:latest

Running behind a reverse proxy

OIDC_BASE_URL must be the externally reachable HTTPS URL, and the proxy must forward the Host header unchanged, otherwise the OAuth metadata this server advertises will point at the wrong host.

Data Sources

Ghostfolio supports multiple data sources for market data and symbols:

• YAHOO - Yahoo Finance data source
• COINGECKO - CoinGecko for cryptocurrency data
• MANUAL - Manually entered data
• And other configured data sources in your Ghostfolio instance

When using tools that require a data source parameter, specify the appropriate source for your asset type.

Using Docker

A Docker image is available on GitHub Packages for easy deployment. It runs the HTTP Streamable transport on port 8000 (/mcp).

docker pull ghcr.io/mhajder/ghostfolio-mcp:latest

When OIDC authentication is enabled, mount a volume on /data so OAuth client registrations survive container recreation.

Open WebUI

Open WebUI 0.6.31 and later connect to the image directly; the separate MCPO image (ghcr.io/mhajder/ghostfolio-mcpo) is no longer published. In Open WebUI, go to Admin Settings > Integrations > External Tool Servers, add a connection of type MCP (Streamable HTTP) with the URL http://<host>:8000/mcp, and set Bearer authentication to your MCP_HTTP_BEARER_TOKEN.

If OIDC authentication is enabled, it takes precedence and the bearer token is not accepted. Use the URL OIDC_BASE_URL + /mcp and choose OAuth 2.1 authentication instead; Open WebUI registers itself as a client, so if you set OIDC_ALLOWED_REDIRECT_URIS, include your Open WebUI URL in it.

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run tests and ensure code quality (uv run pytest && uv run ruff check .)
5. Commit your changes (git commit -m 'Add amazing feature')
6. Push to the branch (git push origin feature/amazing-feature)
7. Open a Pull Request

License

GNU Affero General Public License - see LICENSE file for details.