Skip to main content
Glama
freqtrade-mcp

freqtrade-mcp

@furkankoykiran/freqtrade-mcp

CI npm version GitHub Package License: MIT Node.js

TypeScript MCP server for Freqtrade — connect AI agents (Claude, Cursor, Cline) to your crypto trading bot via its REST API.

Built with the official MCP TypeScript SDK, it exposes 15 tools covering account stats, trade management, market data, pair list control, trade execution, and bot lifecycle — all accessible from any MCP-compatible client.


Features

Category

Tools

Account

get_profit_stats, get_balance, get_performance

Trades

get_open_trades, get_trade, get_trade_history

Market Data

get_market_data

Pair Lists

get_whitelist, get_blacklist, add_to_blacklist, remove_from_blacklist

Execution

execute_trade, force_exit_trade

Lifecycle

start_bot, stop_bot, reload_config, get_bot_info, get_locks, delete_lock


Related MCP server: freqtrade-mcp

Prerequisites

  1. Freqtrade running with the REST API enabled (see Freqtrade REST API docs)

  2. Node.js 18+ (node --version)

Enable the Freqtrade REST API

Add the following to your Freqtrade config.json:

"api_server": {
  "enabled": true,
  "listen_ip_address": "127.0.0.1",
  "listen_port": 8080,
  "verbosity": "error",
  "enable_openapi": false,
  "jwt_secret_key": "change-this-to-a-random-32-char-string",
  "username": "Freqtrader",
  "password": "YourStrongPassword"
}

Installation

Option 1 — Run directly with npx (no install required)

FREQTRADE_PASSWORD=yourpassword npx @furkankoykiran/freqtrade-mcp

Option 2 — Install globally from npm

npm install -g @furkankoykiran/freqtrade-mcp
FREQTRADE_PASSWORD=yourpassword freqtrade-mcp

Option 3 — Install from GitHub Packages

npm install -g @furkankoykiran/freqtrade-mcp --registry=https://npm.pkg.github.com
FREQTRADE_PASSWORD=yourpassword freqtrade-mcp

Option 4 — Build from source

git clone https://github.com/furkankoykiran/freqtrade-mcp.git
cd freqtrade-mcp
npm install
npm run build
node build/index.js

Configuration

The server is configured entirely via environment variables — no config file needed.

Variable

Default

Description

FREQTRADE_API_URL

http://127.0.0.1:8080

Base URL of the Freqtrade API server

FREQTRADE_USERNAME

Freqtrader

API username from your Freqtrade config

FREQTRADE_PASSWORD

(empty)

API password — required

Copy .env.example to .env and fill in your values for local development.


MCP Client Setup

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "freqtrade": {
      "command": "npx",
      "args": ["-y", "@furkankoykiran/freqtrade-mcp"],
      "env": {
        "FREQTRADE_API_URL": "http://127.0.0.1:8080",
        "FREQTRADE_USERNAME": "Freqtrader",
        "FREQTRADE_PASSWORD": "YourStrongPassword"
      }
    }
  }
}

VS Code (Cline / Continue)

Add to your MCP server settings:

{
  "freqtrade": {
    "command": "npx",
    "args": ["-y", "@furkankoykiran/freqtrade-mcp"],
    "env": {
      "FREQTRADE_API_URL": "http://127.0.0.1:8080",
      "FREQTRADE_USERNAME": "Freqtrader",
      "FREQTRADE_PASSWORD": "YourStrongPassword"
    }
  }
}

Built from source

{
  "freqtrade": {
    "command": "node",
    "args": ["/absolute/path/to/freqtrade-mcp/build/index.js"],
    "env": {
      "FREQTRADE_API_URL": "http://127.0.0.1:8080",
      "FREQTRADE_USERNAME": "Freqtrader",
      "FREQTRADE_PASSWORD": "YourStrongPassword"
    }
  }
}

Available Tools

Account

get_profit_stats

Retrieve current profit/loss statistics: total profit, win/loss ratio, best pair, drawdown, trading volume, and more.

get_balance

Retrieve the current account balance across all currencies, including free, used, and total amounts.

get_performance

Retrieve per-pair trading performance metrics, including profit and trade count.

Parameter

Type

Required

Description

pair

string

No

Filter to a specific pair (e.g. BTC/USDT)


Trades

get_open_trades

Retrieve all currently active trades, including entry price, current profit, stake amount, and duration.

get_trade

Retrieve detailed information about a specific trade by its ID.

Parameter

Type

Required

Description

trade_id

number

Yes

Numeric trade ID

get_trade_history

Retrieve closed trade history with optional pagination.

Parameter

Type

Required

Description

limit

number

No

Max trades to return (max 500)

offset

number

No

Pagination offset


Market Data

get_market_data

Retrieve live OHLCV candlestick data for a trading pair.

Parameter

Type

Required

Description

pair

string

Yes

Trading pair (e.g. BTC/USDT)

timeframe

enum

Yes

1m, 5m, 15m, 30m, 1h, 4h, 1d, etc.

limit

number

No

Number of candles (max 500)


Pair Lists

get_whitelist / get_blacklist

Retrieve the current whitelist / blacklist.

add_to_blacklist

Add a trading pair to the blacklist.

Parameter

Type

Required

Description

pair

string

Yes

Pair to blacklist (e.g. ETH/USDT)

remove_from_blacklist

Remove a trading pair from the blacklist.

Parameter

Type

Required

Description

pair

string

Yes

Pair to remove


Trade Execution

execute_trade

Force-enter a trade, bypassing strategy signals. The bot manages the position after entry.

Parameter

Type

Required

Description

pair

string

Yes

Trading pair (e.g. BTC/USDT)

side

long/short

Yes

Trade direction

stake_amount

number

No

Amount in stake currency

price

number

No

Limit price (omit for market order)

order_type

limit/market

No

Order type

Natural language examples:

  • "buy 100 USDT of BTC" → pair=BTC/USDT, side=long, stake_amount=100

  • "short ETH/USDT at 2000" → pair=ETH/USDT, side=short, price=2000

force_exit_trade

Force-exit an open trade. Supports full and partial exits.

Parameter

Type

Required

Description

trade_id

number

Yes

Trade ID to exit

order_type

limit/market

No

Exit order type (default: market)

amount

number

No

Partial exit amount


Bot Lifecycle

start_bot / stop_bot

Start or stop the trading bot.

reload_config

Reload the bot configuration from disk without restarting the process.

get_bot_info

Retrieve bot version and the timestamp of the last strategy run cycle.

get_locks

Retrieve all active trade locks.

delete_lock

Remove a specific trade lock by ID.

Parameter

Type

Required

Description

lock_id

number

Yes

Lock ID to remove


Development

# Clone and install
git clone https://github.com/furkankoykiran/freqtrade-mcp.git
cd freqtrade-mcp
npm install

# Run in development mode (auto-reloads on change)
cp .env.example .env
# Edit .env with your Freqtrade credentials
npm run dev

# Type-check
npm run typecheck

# Lint
npm run lint

# Build for production
npm run build

Testing with MCP Inspector

npx @modelcontextprotocol/inspector node build/index.js

Set the environment variables in the Inspector UI and verify all 15 tools are listed.


Contributing

Contributions are welcome. Please read the contributing guidelines and open an issue before submitting a pull request for significant changes.


License

MIT — see LICENSE.

Available Tools

19 tools
add_to_blacklistB

Add a trading pair to the blacklist to prevent the bot from opening new trades on it.

Inputs: pair (required).

delete_lockA

Remove a specific trade lock by its ID. Use get_locks to list current locks and their IDs.

Inputs: lock_id (required).

execute_tradeA

Manually enter (force-enter) a trade on a specific pair. The bot bypasses strategy signals and opens the position immediately. Natural language examples: • "buy 100 USDT of BTC/USDT" → pair=BTC/USDT, side=long, stake_amount=100 • "short 0.5 ETH/USDT at 2000" → pair=ETH/USDT, side=short, price=2000 The position will be managed by the active strategy after entry.

Inputs: pair (required), side (required), stake_amount, price, +1 more.

force_exit_tradeA

Manually exit (force-sell) an open trade, bypassing the strategy exit signals. Supports full and partial exits. Examples: • Close trade 42 immediately: trade_id=42 • Partial exit 50% of trade 7: trade_id=7, amount=

Inputs: trade_id (required), order_type, amount.

get_balanceA

Check the current wallet and account balance across all currencies, including free, used, and total amounts.

Inputs: no named parameters.

get_blacklistA

View the current trading pair blacklist — pairs that are explicitly excluded from trading.

Inputs: no named parameters.

get_bot_infoA

Get general information about the bot: software version and the timestamp of the last strategy run cycle.

Inputs: no named parameters.

get_locksA

Retrieve all active trade locks. Locks prevent the bot from opening new trades on specific pairs for a defined period.

Inputs: no named parameters.

get_market_dataA

Fetch live OHLCV (Open/High/Low/Close/Volume) candlestick market data for a specific trading pair and timeframe.

Inputs: pair (required), timeframe (required), limit.

get_open_tradesA

View all currently active (open) trades, including entry price, current profit, stake amount, and duration.

Inputs: no named parameters.

get_performanceA

Retrieve per-pair trading performance metrics, including profit and trade count for each pair.

Inputs: pair.

get_profit_statsA

Retrieve current profit and loss statistics: total profit, win/loss ratio, best pair, drawdown, trading volume, and more.

Inputs: no named parameters.

get_tradeA

Retrieve detailed information about a specific trade by its ID, including full history, fees, and profit/loss.

Inputs: trade_id (required).

get_trade_historyA

Retrieve closed trade history with optional pagination. Returns trades sorted by ID.

Inputs: limit, offset.

get_whitelistA

View the current trading pair whitelist — the set of pairs the bot is allowed to trade.

Inputs: no named parameters.

reload_configA

Reload the bot configuration from disk. Useful after editing config.json without restarting the process. The bot will briefly pause trading during the reload.

Inputs: no named parameters.

remove_from_blacklistB

Remove a trading pair from the blacklist, allowing the bot to trade it again.

Inputs: pair (required).

start_botA

Start the Freqtrade bot. The bot will begin trading according to its configured strategy. Has no effect if already running.

Inputs: no named parameters.

stop_botA

Stop the Freqtrade bot. Existing open trades will remain open and will not be closed automatically. Use force_exit_trade to close positions manually.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 19 tools

    Disambiguation5/5

    Each tool targets a distinct action or resource. Blacklist, lock, trade execution, and bot control tools are clearly separated. Even similar tools like get_performance and get_profit_stats are differentiated by per-pair vs global perspective.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (e.g., get_balance, add_to_blacklist, force_exit_trade). No mixing of conventions like camelCase or inconsistent verb forms.

    Tool Count4/5

    19 tools is slightly above the ideal range but still reasonable for a comprehensive trading bot server. Each tool covers a necessary function without redundancy.

    Completeness4/5

    Core CRUD operations for trades, blacklist, locks, and bot control are present. Minor gaps exist, such as the inability to modify active trade parameters (e.g., stop loss) or cancel pending orders, but the essential workflow is covered.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that provides AI agents with financial tools including real-time quotes, backtesting, technical analysis, and multi-exchange data via a simple CLI interface.
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server for cryptocurrency trading via Freqtrade, enabling trade management, balance checks, strategy configuration, backtesting, and bot lifecycle control from any MCP-compatible AI agent.
      MIT