How to install maverick-mcp?
wshobson/maverick-mcp
$git clone https://github.com/wshobson/maverick-mcpInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install maverick-mcp by running `git clone https://github.com/wshobson/maverick-mcp`, then use it for the current task and follow its documentation at https://github.com/wshobson/maverick-mcp.
README.md
| 1 | <!-- mcp-name: io.github.wshobson/maverick-mcp --> |
| 2 | |
| 3 | # MaverickMCP - Personal Stock Analysis MCP Server |
| 4 | |
| 5 | [](https://opensource.org/licenses/MIT) |
| 6 | [](https://www.python.org/downloads/) |
| 7 | [](https://github.com/jlowin/fastmcp) |
| 8 | [](https://github.com/wshobson/maverick-mcp) |
| 9 | [](https://github.com/wshobson/maverick-mcp/issues) |
| 10 | [](https://github.com/wshobson/maverick-mcp/network/members) |
| 11 | |
| 12 | **MaverickMCP** is a personal-use FastMCP server that provides financial data |
| 13 | analysis, technical indicators, stock screening, and portfolio tracking tools |
| 14 | directly to your Claude Desktop interface. Built for individual traders and |
| 15 | investors, it runs entirely on your own machine with no authentication or |
| 16 | billing complexity. |
| 17 | |
| 18 | Core tools need no API key: market data comes from `yfinance`. Two optional |
| 19 | extras add more: `[backtesting]` (VectorBT-powered strategy backtesting) and |
| 20 | `[research]` (LangGraph-based deep research, bring-your-own LLM key). |
| 21 | |
| 22 | ## Skip the setup — hosted version |
| 23 | |
| 24 | Self-hosting MaverickMCP means Python, uv, and MCP client config (Redis and a |
| 25 | research LLM key are optional). If you just want the analysis, [Capital Companion](https://capitalcompanion.ai) |
| 26 | is the hosted product built on the same engine: AI technical analysis, trade-plan |
| 27 | review sheets with outcome tracking, and price alerts. **25 free analyses, |
| 28 | no credit card.** |
| 29 | |
| 30 | Self-hosting instructions continue below. |
| 31 | |
| 32 | ## Why MaverickMCP? |
| 33 | |
| 34 | **Key Benefits:** |
| 35 | |
| 36 | - **No Setup Complexity**: `make dev` gets the server running; no database |
| 37 | migrations, no seed scripts, no API key required for core tools. |
| 38 | - **Modern Python Tooling**: Built with `uv` for fast dependency management. |
| 39 | - **Claude Desktop Integration**: Native MCP support via stdio or streamable |
| 40 | HTTP. |
| 41 | - **37 Core Tools**: Market data, technical analysis, screening, portfolio |
| 42 | tracking with a risk dashboard, watchlists, and a trade journal. |
| 43 | - **Optional Extras**: 12 backtesting tools and 3 research tools, each fully |
| 44 | opt-in via `pip install`/`uv sync` extras. |
| 45 | - **Smart Caching**: Tiered cache (memory, then Redis or SQLite) with |
| 46 | graceful fallback when Redis isn't running. |
| 47 | - **Open Source**: MIT licensed. |
| 48 | |
| 49 | ## Features |
| 50 | |
| 51 | - **Stock Data Access**: Historical and real-time quotes with intelligent |
| 52 | caching (`yfinance`, no API key required). |
| 53 | - **Technical Analysis**: RSI, MACD, support/resistance, and a combined |
| 54 | full-analysis tool. |
| 55 | - **Stock Screening**: Maverick bullish, bearish, and supply/demand |
| 56 | strategies, computed over the tickers you've already queried. |
| 57 | - **Portfolio Tracking**: Positions with average cost-basis, live P&L, a |
| 58 | risk dashboard, watchlists, and a trade journal. |
| 59 | - **Backtesting** (`[backtesting]` extra): VectorBT engine, 12 rule-based |
| 60 | strategy templates plus 8 ML strategy classes, optimization, walk-forward |
| 61 | analysis, and Monte Carlo simulation. |
| 62 | - **Research** (`[research]` extra): LangGraph-based deep research over |
| 63 | companies, sectors, and market sentiment, backed by Exa web search and a |
| 64 | bring-your-own LLM. |
| 65 | - **Multi-Transport Support**: Streamable HTTP and STDIO. |
| 66 | |
| 67 | ## Quick Start |
| 68 | |
| 69 | ### Prerequisites |
| 70 | |
| 71 | - **Python 3.12+**: Core runtime environment |
| 72 | - **[uv](https://docs.astral.sh/uv/)**: Modern Python package manager (recommended) |
| 73 | - Redis (optional, for enhanced caching) |
| 74 | - PostgreSQL or SQLite (optional, for data persistence; SQLite is the default) |
| 75 | |
| 76 | #### Installing uv (Recommended) |
| 77 | |
| 78 | ```bash |
| 79 | # macOS/Linux |
| 80 | curl -LsSf https://astral.sh/uv/install.sh | sh |
| 81 | |
| 82 | # Windows |
| 83 | powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" |
| 84 | |
| 85 | # Alternative: via pip |
| 86 | pip install uv |
Related
6 picksType
- financetoolkit200+ transparent financial metrics calculated from raw statements, not third-party endpoints.Jul 2026
- mcp-serverAn MCP server for interacting with the Financial Datasets stock market API.Jun 2025
- mcp-serverPython MCP server for local interactions with the QuantConnect API.May 2026
- alpaca-mcp-serverAlpaca Trading API integration for Model Context Protocol (MCP). V2 generates 60+ tools directly from Alpaca's OpenAPI specs using FastMCP.Jul 2026
- finopsmcpSee where your cloud and AI bills go, and spend less. Local-first, in your terminal or editor.Jul 2026
- xero-mcp-serverMCP server implementation for Xero integrationJun 2026
