Integrates with LangChain agents through MCPToolkit, enabling AI agents to access ForexFactory economic calendar data for trading and financial analysis workflows
Provides MCP-compatible access to ForexFactory economic calendar events for automation workflows and trading pipelines
π 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.
π Features
β Retrieve economic calendar events by time period (
today
,this_week
,custom
, etc.)β Access via MCP resources (for subscription-style access)
β Access via MCP tools (direct calls from clients/agents)
β JSON-first responses for easy integration
β‘ Integrates with LangChain, n8n, or any MCP-compatible client
π 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.
(See repo for full details β this is a high-level layout for contributors.)
π§ Installation
Requirements
Python 3.12+
uv or pip
A modern terminal or MCP-compatible client
Setup
βΆοΈ Usage
β‘ Quickstart
Start the server with default settings (stdio
transport):
Run with HTTP transport:
SSE transport (β οΈ deprecated)
Environment variable defaults
π·οΈ Namespace
Default namespace:
Override via .env
:
π¦ Resources
Name | Path | Description |
|
| Todayβs events |
|
| All events this week |
|
| Custom date range |
π οΈ Tools
Name | Type | Description |
| Tool | Retrieve events for a given period |
Supported values:
π Prompts
Name | Description |
| Trader prep note for today |
| Weekly macro event summary |
| Weekly event-risk heatmap |
| Scenario map for specific events |
π§© Prompt Styles
All prompts support a style
parameter to control formatting.
Default:
See the Output Style Reference for available formats.
π» Client Examples
Example: Using MCP CLI
Example: Using in Python
Example: LangChain Integration
π Client Configuration Reference
Includes:
β Example configs for Claude Desktop (local + Docker)
π³ Docker build and setup
π§© VS Code MCP integration (future)
π§ͺ Testing + troubleshooting checklist
π Inspector setup for visual debugging
βοΈ Configuration
Variable | Default | Description |
|
| Namespace prefix |
|
| Transport type (
,
,
) |
|
| Host for HTTP/SSE |
|
| Port for HTTP/SSE |
|
| Playwright timeout |
| System local | Timezone override |
Example .env
π³ Docker Integration
Supports both stdio (default) and HTTP/SSE.
Runs MCP server and exposes it on port 8000.
Target | Description |
| Build Docker image |
| Run server in HTTP mode |
| Run in stdio mode |
| Inspect via MCP Inspector |
| Stop containers |
π 1. uv
or dependency install fails
Run:
β‘ 2. Server exits immediately
Switch to:
π 3. Port in use
Change port:
π 4. Browser fails
Install Chromium:
π§ͺ Testing
π Roadmap
Event filters by currency and impact
Historical backfill
MCP prompt expansions
Cloud-ready deployment
π€ Contributing
Fork the repo
Create a feature branch
Commit with a clear message
Push and open a PR
π License
MIT License β see LICENSE for details.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables access to ForexFactory economic calendar data through MCP resources and tools. Supports retrieving economic events by time periods for integration with trading assistants and agentic workflows.