Forexfactory

📅 ForexFactory MCP Server

An MCP (Model Context Protocol) server that exposes ForexFactory economic calendar data as resources and tools.

Designed for use in agentic workflows, LLMs, and trading assistants.

• 📅 ForexFactory MCP Server
  • 🚀 Features
    • 📌 Development Status
  • 🔧 Installation
    • Requirements
    • Setup
  • ▶️ Usage
    • ⚡ Quickstart
    • SSE transport (⚠️ deprecated)
    • Environment variable defaults
  • 🏷️ Namespace
  • 📦 Resources
  • 🛠️ Tools
  • 📝 Prompts
    • 🧩 Prompt Styles
  • 💻 Client Examples
    • Example: Using MCP CLI
    • Example: Using in Python
    • Example: LangChain Integration
    • 📘 Client Configuration Reference
  • ⚙️ Configuration
    • Example .env
  • 🐳 Docker Integration
    • 🐍 1. uv or dependency install fails
    • ⚡ 2. Server exits immediately
    • 🌐 3. Port in use
    • 🔐 4. Browser fails
  • 🧪 Testing
  • 📊 Roadmap
  • 🤝 Contributing
  • 📜 License

🚀 Features

• ✅ Retrieve economic calendar events by time period (today, this_week, custom, etc.)
• ✅ Access via MCP resources (for subscription-style access)
• ✅ Access via MCP tools (direct calls from clients/agents)
• ✅ JSON-first responses for easy integration
• ⚡ Integrates with LangChain, n8n, or any MCP-compatible client

📌 Development Status

This project is actively developed. The core functionality is stable (retrieving ForexFactory economic calendar events via MCP tools and resources), but we are still:

• Expanding features (prompts, deployment options)
• Improving documentation and examples

We welcome feedback and contributions while we continue building out the ecosystem.

forexfactory-mcp/
│── src/forexfactory_mcp/   # Main package
│   ├── models/             # Schemas & enums
│   ├── services/           # Scraper + data normalization
│   ├── tools/              # MCP tool definitions
│   ├── resources/          # MCP resource definitions
│   ├── prompts/            # Prompt templates (optional MCP prompts)
│   ├── utils/              # Shared helpers & config
│   └── server.py           # FastMCP server entrypoint
│
│── examples/               # Example clients
│── tests/                  # Unit tests
│── .env.example            # Copy to .env for config
│── pyproject.toml          # Dependencies & metadata
│── README.md               # Documentation
│── .python-version         # Python version pin (3.12)

(See repo for full details — this is a high-level layout for contributors.)

🔧 Installation

Requirements

• Python 3.12+
• uv or pip
• A modern terminal or MCP-compatible client

Setup

# Clone repo
git clone https://github.com/kjpou1/forexfactory-mcp.git
cd forexfactory-mcp

# Install dependencies
uv sync   # or: pip install -e .

# Install Playwright browser binaries
uv run playwright install chromium
# or, if using pip/venv:
playwright install chromium

# Copy example environment and adjust if needed
cp .env.example .env

▶️ Usage

⚡ Quickstart

Start the server with default settings (stdio transport):

uv run ffcal-server

Run with HTTP transport:

uv run ffcal-server --transport http --host 0.0.0.0 --port 8080

SSE transport (⚠️ deprecated)

uv run ffcal-server --transport sse --host 127.0.0.1 --port 8001

Environment variable defaults

MCP_TRANSPORT=http
MCP_HOST=0.0.0.0
MCP_PORT=8080

🏷️ Namespace

Default namespace:

ffcal

Override via .env:

NAMESPACE=ffcal

📦 Resources

🛠️ Tools

Supported values:

today, tomorrow, yesterday, this_week, next_week, last_week, this_month, next_month, last_month, custom

📝 Prompts

🧩 Prompt Styles

All prompts support a style parameter to control formatting. Default:

style: str = "bullet points"

See the Output Style Reference for available formats.

💻 Client Examples

Example: Using MCP CLI

mcp call ffcal:get_calendar_events time_period=this_week

Example: Using in Python

from mcp.client.session import Session
async with Session("ws://localhost:8000") as session:
    result = await session.call_tool("ffcal:get_calendar_events", {"time_period": "today"})
    print(result)

Example: LangChain Integration

from langchain.agents import initialize_agent
from langchain_mcp import MCPToolkit

toolkit = MCPToolkit.from_server_url("ws://localhost:8000", namespace="ffcal")
agent = initialize_agent(toolkit.tools)
response = agent.run("What are today's USD-related high impact events?")
print(response)

📘 Client Configuration Reference

📖 docs/CLIENT_CONFIG_REFERENCE.md

Includes:

• ✅ Example configs for Claude Desktop (local + Docker)
• 🐳 Docker build and setup
• 🧩 VS Code MCP integration (future)
• 🧪 Testing + troubleshooting checklist
• 🔍 Inspector setup for visual debugging

⚙️ Configuration

Example .env

MCP_TRANSPORT=http
MCP_HOST=0.0.0.0
MCP_PORT=8080
NAMESPACE=ffcal

🐳 Docker Integration

Supports both stdio (default) and HTTP/SSE.

docker compose build
docker compose up forexfactory_mcp

Runs MCP server and exposes it on port 8000.

🐍 1. uv or dependency install fails

Run:

docker compose build --no-cache forexfactory_mcp

⚡ 2. Server exits immediately

Switch to:

make run-http

🌐 3. Port in use

Change port:

docker compose run --rm -e MCP_PORT=8080 forexfactory_mcp

🔐 4. Browser fails

Install Chromium:

docker compose run forexfactory_mcp playwright install chromium

🧪 Testing

pytest -v

📊 Roadmap

• Event filters by currency and impact
• Historical backfill
• MCP prompt expansions
• Cloud-ready deployment

🤝 Contributing

1. Fork the repo
2. Create a feature branch
3. Commit with a clear message
4. Push and open a PR

📜 License

MIT License – see LICENSE for details.