Freqtrade-MCP
Integrates with the Freqtrade cryptocurrency trading bot via its REST API to enable AI-driven automated trading and bot management. It allows users to fetch market data, monitor performance, manage whitelists, and execute trades through natural language.
README
Freqtrade-MCP
An MCP server that integrates with the Freqtrade cryptocurrency trading bot via its REST API, enabling seamless AI agent interaction for automated trading operation.
For more crypto-related MCP servers, see the Kukapay MCP servers.
Installation
Prerequisites
- Python 3.13+: Ensure Python is installed on your system.
- Freqtrade: A running Freqtrade instance with the REST API enabled (see Freqtrade Docs).
- Git: For cloning the repository.
Steps
-
Clone the Repository:
git clone https://github.com/kukapay/freqtrade-mcp.git cd freqtrade-mcp -
Install Dependencies: Using
pip:pip install freqtrade-client mcp[cli]Or with
uv(optional):uv add freqtrade-client "mcp[cli]" -
Client Configuration:
"mcpServers": { "freqtrade-mcp": { "command": "uv", "args": [ "--directory", "/your/path/to/freqtrade-mcp", "run", "__main__.py" ], "env": { "FREQTRADE_API_URL": "http://127.0.0.1:8080", "FREQTRADE_USERNAME": "your_username", "FREQTRADE_PASSWORD": "your_password" } } } -
Freqtrade Configuration:
Enable the rest API by adding the api_server section to your configuration and setting api_server.enabled to true.
Sample configuration:
"api_server": { "enabled": true, "listen_ip_address": "127.0.0.1", "listen_port": 8080, "verbosity": "error", "enable_openapi": false, "jwt_secret_key": "somethingrandom", "CORS_origins": [], "username": "Freqtrader", "password": "SuperSecret1!", "ws_token": "sercet_Ws_t0ken" },Check the document here.
Usage
Available Tools
The server exposes the following Freqtrade API endpoints as MCP tools:
| Tool | Description | Parameters |
|---|---|---|
fetch_market_data |
Fetch OHLCV data for a pair | pair: str, timeframe: str |
fetch_bot_status |
Get open trade status | None |
fetch_profit |
Get profit summary | None |
fetch_balance |
Get account balance | None |
fetch_performance |
Get performance metrics | None |
fetch_whitelist |
Get whitelist of pairs | None |
fetch_blacklist |
Get blacklist of pairs | None |
fetch_trades |
Get trade history | None |
fetch_config |
Get bot configuration | None |
fetch_locks |
Get trade locks | None |
place_trade |
Place a buy/sell trade | pair: str, side: str, stake_amount: float |
start_bot |
Start the bot | None |
stop_bot |
Stop the bot | None |
reload_config |
Reload bot configuration | None |
add_blacklist |
Add pair to blacklist | pair: str |
delete_blacklist |
Remove pair from blacklist | pair: str |
delete_lock |
Delete a trade lock | lock_id: int |
run_backtest |
Start backtest via REST API | strategy: str, enable_protections: bool, optional timerange, timeframe |
fetch_backtest_status |
Get current backtest status/result | None |
fetch_backtest_history |
List backtest history | optional filename: str |
abort_backtest |
Abort currently running backtest | None |
reset_backtest |
Reset backtest state/result | None |
Example Prompts
-
Fetch Market Data:
- "Show me the hourly price data for BTC/USDT."
- "What’s the 5-minute chart for ETH/BTC like?"
- "Give me the latest candlestick data for XRP/USDT over the past hour."
-
Fetch Bot Status:
- "What’s the current status of my open trades?"
- "Are there any active trades right now?"
- "Tell me about the bot’s trading activity at the moment."
-
Fetch Profit:
- "How much profit have I made so far?"
- "What’s the total profit summary for the bot?"
- "Can you show me my trading gains?"
-
Fetch Balance:
- "What’s my account balance?"
- "How much money do I have in the trading account?"
- "Tell me the current balance of my Freqtrade wallet."
-
Fetch Performance:
- "How well has the bot been performing?"
- "What are the performance metrics for my trades?"
- "Show me the trading stats."
-
Fetch Whitelist:
- "Which pairs are on the whitelist?"
- "What trading pairs is the bot allowed to use?"
- "List the whitelisted pairs for me."
-
Fetch Blacklist:
- "Which pairs are blacklisted?"
- "What trading pairs are blocked right now?"
- "Tell me about the blacklist."
-
Fetch Trades:
- "What’s the history of my closed trades?"
- "Show me all the trades the bot has completed."
- "Can you list my past trades?"
-
Fetch Config:
- "What’s the current bot configuration?"
- "Show me the settings the bot is using."
- "Tell me about the Freqtrade config."
-
Fetch Locks:
- "Are there any trade locks active?"
- "What locks are currently in place?"
- "Show me the list of trading locks."
-
Place Trade:
- "Buy 0.01 BTC/USDT right now."
- "Sell 0.05 ETH/USDT immediately."
- "Place a buy order for 0.1 XRP/USDT."
-
Start Bot:
- "Start the trading bot."
- "Turn on the Freqtrade bot."
- "Get the bot running now."
-
Stop Bot:
- "Stop the trading bot."
- "Shut down the Freqtrade bot."
- "Pause the bot’s trading."
-
Reload Config:
- "Reload the bot’s configuration."
- "Update the bot settings."
- "Refresh the Freqtrade config."
-
Add Blacklist:
- "Blacklist ETH/USDT."
- "Add BTC/ETH to the blacklist."
- "Block trading for XRP/USDT."
-
Delete Blacklist:
- "Remove ETH/USDT from the blacklist."
- "Unblock BTC/ETH for trading."
- "Take XRP/USDT off the blacklist."
-
Delete Lock:
- "Delete the trade lock with ID 123."
- "Remove lock number 45."
- "Unlock the trade with ID 7."
License
This project is licensed under the MIT License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.