Coinbase Trade Assistant MCP
Provides intelligent cryptocurrency trading assistance using Coinbase Advanced Trade API, with automated technical analysis screening and real-time market insights.
README
Coinbase Trade Assistant MCP
A sophisticated Model Context Protocol (MCP) server that provides intelligent cryptocurrency trading assistance using Coinbase Advanced Trade API. Features automated technical analysis screening and real-time market insights.
Features
-
Intelligent Auto-Screener: Efficiently scans all available coins for high-probability technical setups
- 13 EMA crosses above 55 SMA (trend confirmation)
- RSI recovery from oversold levels (< 10)
- Volume pattern analysis (unusual activity detection)
- Typically returns 0-30 qualified coins depending on market conditions
-
Smart Filtering: Focus on actionable opportunities, not information overload
-
Real-time Market Data: Live price and volume data from Coinbase Advanced Trade API
-
Due Diligence Ready: Curated list for manual review and selection
-
Risk-Aware: Built-in volume and volatility filters
Quick Start
-
Configure API Keys:
- Get your free Coinbase CDP API keys from Coinbase Developer Platform
- More info docs.cdp.coinbase.com/get-started/authentication/cdp-api-keys#creating-secret-api-keys
- Go to the advanced settings when getting your key and make sure to select "ECDSA"
- Copy your
cdp_api_key.jsonfile to the project directory - That's it! No environment variables needed.
-
Add to Claude Desktop:
{ "mcpServers": { "coinbase-trade-assistant": { "command": "uv", "args": [ "--directory", "/path/to/coinbase-trade-assistant-mcp", "run", "main.py" ] } } } -
Install Dependencies- if there is an issue or you are not using the client config which should do this automatically:
cd coinbase-trade-assistant-mcp uv venv --python 3.12 --seed source .venv/bin/activate uv sync
Screening Criteria
The screener uses a confluence-based approach requiring multiple confirming signals:
- Trend: 13 EMA crossing above 55 SMA (momentum shift)
- Momentum: RSI recovery from oversold (< 10) back above 10-30 range
- Volume: Unusual volume activity (3x+ average or very low < 20%)
- Signal Strength: Requires 2 out of 3 conditions for qualification
Expected Results:
- Bull Markets: 15-30 qualified coins
- Bear/Sideways Markets: 0-10 qualified coins
- Transition Periods: 5-15 qualified coins
All results ranked by signal strength for efficient due diligence.
Tools Available
Primary Workflow:
screen_all_coins: Main tool - Run comprehensive technical screening across all marketscheck_signals: Review and analyze recent screening resultsmonitor_portfolio: Track specific watchlist for signals
Supporting Tools:
get_market_data: Current market snapshots for specific coinsanalyze_coin: Basic technical data for individual coins (when needed)
Requirements
- Python 3.12+
- Coinbase CDP API keys
- Claude Desktop or compatible MCP client
Security
- API keys are read from local
cdp_api_key.jsonfile - Never commit your API key file to version control
- The key file is automatically ignored by git (added to .gitignore)
- Rate limiting and error handling built-in
- If sharing your project, remove the key file first
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.