Skip to main content
Glama

ForexFactory MCP Server

by kjpou1

πŸ“… ForexFactory MCP Server

Python License MCP uv

Contributions welcome Status PRs Welcome Made with Love

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.


πŸš€ Features

  • βœ… Retrieve economic calendar events by time period (today, this_week, custom, etc.)

  • βœ… Access via MCP resources (for subscription-style access)

  • βœ… Access via MCP tools (direct calls from clients/agents)

  • βœ… JSON-first responses for easy integration

  • ⚑ Integrates with LangChain, n8n, or any MCP-compatible client


πŸ“Œ 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.


πŸ“‚ Project Structure

forexfactory-mcp/ │── src/forexfactory_mcp/ # Main package β”‚ β”œβ”€β”€ models/ # Schemas & enums β”‚ β”œβ”€β”€ services/ # Scraper + data normalization β”‚ β”œβ”€β”€ tools/ # MCP tool definitions β”‚ β”œβ”€β”€ resources/ # MCP resource definitions β”‚ β”œβ”€β”€ prompts/ # Prompt templates (optional MCP prompts) β”‚ β”œβ”€β”€ utils/ # Shared helpers & config β”‚ └── server.py # FastMCP server entrypoint β”‚ │── 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 β€” this is a high-level layout for contributors.)


πŸ”§ Installation

Requirements

  • Python 3.12+ (see .python-version for exact version)

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

▢️ Usage

Start the MCP server

uv run forexfactory_mcp.server

The server will expose MCP resources, prompts, and tools that clients can call.


🏷️ Namespace

This MCP server registers under the namespace:

ffcal

You can override this in your .env file:

NAMESPACE=ffcal

All tools and resources are exposed with this prefix.

Examples:

  • ffcal:get_calendar_events

  • ffcal:events_week

  • ffcal:events_today


πŸ› οΈ Tools & Resources

Name

Type

Description

Parameters

events_today

Resource

Fetch today’s calendar events

None

events_week

Resource

Fetch this week’s events

None

get_calendar_events

Tool

Retrieve events for a given period

time_period

(str),

start_date

(YYYY-MM-DD),

end_date

(YYYY-MM-DD)

Supported time_period values

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

When custom is used, you must pass start_date and end_date.


πŸ’» 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)

βš™οΈ Configuration

No special config is required, but you may set environment variables.

Variable

Default

Description

NAMESPACE

ffcal

MCP namespace for tools/resources

SCRAPER_TIMEOUT_MS

5000

Timeout for Playwright (milliseconds)

LOCAL_TIMEZONE

system local (fallback UTC)

Local timezone override (e.g.,

Europe/Luxembourg

)

INCLUDE_FIELDS

(empty β†’ default fields)

Comma-separated list of fields to include, or

*

for all fields

EXCLUDE_FIELDS

(empty β†’ none)

Comma-separated list of fields to exclude (applied after INCLUDE_FIELDS)


Include/Exclude Fields

You can control which event fields are returned by the MCP server using INCLUDE_FIELDS and EXCLUDE_FIELDS.

Processing Rules

  1. If both are empty β†’ the server returns a default lean set:

    id, title, currency, impact, datetime, forecast, previous, actual
  2. If INCLUDE_FIELDS=* β†’ all available fields are included.

  3. If INCLUDE_FIELDS β†’ only the specified fields are included. Example:

    INCLUDE_FIELDS=id,name,currency,date,forecast,previous,actual
  4. If both β†’

    • First, apply INCLUDE_FIELDS.

    • Then, remove any fields listed in EXCLUDE_FIELDS.

Example Configurations

# Default lean set (no INCLUDE/EXCLUDE set) INCLUDE_FIELDS= EXCLUDE_FIELDS= # All fields INCLUDE_FIELDS=* EXCLUDE_FIELDS= # Minimal fields INCLUDE_FIELDS=id,name,currency,date,forecast,previous,actual # Include impact fields, but exclude noisy metadata INCLUDE_FIELDS=impactName,impactClass,date,currency EXCLUDE_FIELDS=dateline,hasLinkedThreads

Supported Fields

Category

Fields

Identity

id

,

ebaseId

,

title

,

name

,

prefixedName

,

trimmedPrefixedName

Titles

soloTitle

,

soloTitleFull

,

soloTitleShort

Metadata

notice

,

dateline

,

country

,

currency

Links

url

,

soloUrl

,

editUrl

,

hasLinkedThreads

,

siteId

Status Flags

hasNotice

,

hasDataValues

,

hasGraph

,

checkedIn

,

isMasterList

,

firstInDay

,

greyed

,

upNext

Impact

impact

,

impactName

,

impactClass

,

impactTitle

Timing

datetime

,

timeLabel

,

timeMasked

,

date

Values

actual

,

previous

,

revision

,

forecast

,

leaked

,

actualBetterWorse

,

revisionBetterWorse

Display

showGridLine

,

hideHistory

,

hideSoloPage

,

showDetails

,

showGraph

,

enableDetailComponent

,

enableExpandComponent

,

enableActualComponent

,

showExpanded


Example .env

# ===================================================== # 🌐 MCP Namespace # ===================================================== # Namespace prefix for all tools and resources. # Default: ffcal NAMESPACE=ffcal # ===================================================== # βš™οΈ Scraper Configuration # ===================================================== # Timeout for Playwright in milliseconds # Default: 5000 (5s) SCRAPER_TIMEOUT_MS=2000 # Local timezone override (uses system local if not set) # Example: Europe/Luxembourg #LOCAL_TIMEZONE=Europe/Luxembourg # ===================================================== # πŸ“Š Event Fields # ===================================================== # Control which fields to include/exclude in normalized event data. # - If both are empty, only the default lean set of fields is included. # - If INCLUDE_FIELDS=* β†’ all fields are included. # - If both are set, INCLUDE_FIELDS is applied first, then EXCLUDE_FIELDS removes fields. INCLUDE_FIELDS= EXCLUDE_FIELDS= # Example usage: # INCLUDE_FIELDS=id,name,country,currency,date,actual,forecast,previous # EXCLUDE_FIELDS=notice,dateline,hasLinkedThreads,checkedIn,firstInDay

πŸ§ͺ Testing

pytest -v

πŸ“Š Roadmap

  • Event filters by currency and impact

  • Historical event backfill

  • In-memory caching (to reduce repeated scraping)

  • Docker container for deployment

  • MCP prompts for querying events in natural language


🀝 Contributing

  1. Fork this repo

  2. Create a feature branch: git checkout -b feature/my-feature

  3. Commit changes: git commit -m "Add my feature"

  4. Push branch: git push origin feature/my-feature

  5. Open a Pull Request


πŸ“œ License

MIT License – see LICENSE for details.

-
security - not tested
F
license - not found
-
quality - not tested

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.

  1. πŸš€ Features
    1. πŸ“Œ Development Status
    2. πŸ“‚ Project Structure
  2. πŸ”§ Installation
    1. Requirements
    2. Setup
  3. ▢️ Usage
    1. Start the MCP server
  4. 🏷️ Namespace
    1. πŸ› οΈ Tools & Resources
      1. Supported time_period values
    2. πŸ’» Client Examples
      1. Example: Using MCP CLI
      2. Example: Using in Python
      3. Example: LangChain Integration
    3. βš™οΈ Configuration
      1. Include/Exclude Fields
      2. Supported Fields
      3. Example .env
    4. πŸ§ͺ Testing
      1. πŸ“Š Roadmap
        1. 🀝 Contributing
          1. πŸ“œ License

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/kjpou1/forexfactory-mcp'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server