MaverickMCP

An MCP server for personal stock analysis: market data, technical indicators, screening and portfolio tracking, no keys for the core

  • 727 ★ on the repository
  • Last commit
  • MIT
MCP server

Extended access

Why this level

  • Reaches market data from external sources
  • Tracks a portfolio but executes no trades
All reasons and checks

wshobson/maverick-mcp

Install

Manual install

uvx --from "git+https://github.com/wshobson/maverick-mcp@v1.1.0" maverick-mcp --transport stdio

Needs Python 3.12+ and uv. Extras: [backtesting] and [research]; research needs an LLM key.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reaches market data from external sources
  • Tracks a portfolio but executes no trades

This is third-party code. Review the repository files before installing.

What it does

MaverickMCP is a personal-use MCP server built on FastMCP that gives any MCP client financial data analysis tools. It can pull market data, compute technical indicators, screen stocks and track a portfolio. The server runs entirely on your machine with no authentication or billing, and the core tools need no keys because data comes from yfinance. Optional extras add VectorBT strategy backtesting and LangGraph deep research with your own LLM key.

Who it is for. For individual traders and investors who want stock analysis through an MCP client on their own machine.

Good fit when

  • You need market data and technical indicators through MCP
  • You need stock screening and portfolio tracking locally
  • You need strategy backtesting or deep research on a stock

Not a fit when

  • You want a tool that executes trades rather than analyzing
  • You are not ready to set up Python, uv and an MCP client

Example request

Compute technical indicators for this stock and screen by the given conditions

MCP

Transport
stdio
Authentication
not required

Limitations

The server is for personal use; it analyzes data but does not execute trades. Installation needs Python 3.12+ and uv, and core data comes from yfinance. Backtesting and research are optional extras, and research needs your own LLM key. A separate hosted product, Capital Companion, runs on the same engine.

How to disable. Remove the MCP entry from the client config; for an installed package, remove it via the package manager.

FAQ

Is an API key needed?

Not for the core tools; data comes from yfinance. An LLM key is only needed for the optional research module.

Does it execute trades?

No. MaverickMCP analyzes data, indicators and a portfolio but does not buy or sell.

Discussion

No questions or reviews yet.

Official

A financial analysis MCP server: 500+ methods from company statements, ratios, indicators, risk metrics and macro data

MCP serverExtended access5.5KRepository stars

An MCP server for market data and technical analysis: quotes, indicators, screeners and backtesting for stocks, crypto, forex and futures

MCP serverExtended access5.3KRepository stars

Financial data MCP server: stocks, funds, bonds, macro indicators, news and crypto via Tushare and Binance

MCP serverBroad access871Repository stars

MCP server that gives an agent Yahoo Finance data by ticker: price history, financial statements and option chains

MCP serverExtended access369Repository stars

Financial Datasets MCP

Financial Datasets MCP Server

Official

An MCP server for the Financial Datasets API: company financials, stock and crypto prices and news for the agent

MCP serverExtended access2.3KRepository stars

The yfmcp MCP server with Yahoo Finance data: quotes, statements, news, options, holders and charts as images

MCP serverMinimal access209Repository stars

README in short

The README describes MaverickMCP as a FastMCP-based personal stock analysis MCP server available to any MCP client. It provides market data, technical indicators, screening and portfolio tracking and runs entirely on the user's machine with no authentication. Core tools need no keys, data comes from yfinance, and optional extras add VectorBT backtesting and LangGraph research with your own LLM key. Install is via uvx from a release tag, from source or as a package, with a separate hosted product Capital Companion.

README badge

Report a problem