MaverickMCP offers a comprehensive suite of local stock analysis tools covering technical analysis, screening, portfolio management, and optional extras. Strengths: no API key needed for core features, rich toolset, and multi-client integration. Weaknesses: screening requires manual history fetching, and backtesting/research extras require additional install and API keys. Overall, it's a powerful and flexible tool for personal investment analysis.
Strongest · Documentation 12/20 Weakest · Reliability 4/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime：Python 3.12+ · Node.js · Docker
LLM_API_KEY
Optional API key required once LLM_PROVIDER is set; bring your own LLM key.
EXA_API_KEY
Optional Exa web search key for the research extra; get one at https://exa.ai.
DATABASE_URL
Optional database URL; defaults to SQLite (sqlite:///maverick.db), PostgreSQL supported for performance.
REDIS_HOST
Optional Redis host enabling enhanced caching; falls back to in-memory caching if unset.
REDIS_PORT
Optional Redis port, default 6379.
LLM_PROVIDER
Optional LLM provider for the research extra (anthropic, openai, openrouter, openai_compatible).
LLM_MODEL
Optional model name for the configured LLM_PROVIDER.
LLM_BASE_URL
Optional base URL override, required when LLM_PROVIDER=openai_compatible.
LLM_TEMPERATURE
Optional sampling temperature, default 0.0.
LOG_LEVEL
Optional logging verbosity, default INFO.
Requires Python 3.12+ and uv. Core install: uv sync --extra dev (or pip install "maverick-mcp-server"). Optional extras: --extra backtesting, --extra research. Copy .env.example to .env and configure (optional). Start: make dev (HTTP) or make dev-stdio (stdio). Add the JSON config to Claude Desktop.
{
"mcpServers": {
"maverick-mcp": {
"command": "uvx",
"args": [
"--from",
"maverick-mcp-server",
"maverick-mcp",
"--transport",
"stdio"
]
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"maverick-mcp": {
"command": "uvx",
"args": [
"--from",
"maverick-mcp-server",
"maverick-mcp",
"--transport",
"stdio"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add maverick-mcp -- uvx --from maverick-mcp-server maverick-mcp --transport stdio
Run it in a terminal; replace any <…> placeholders with your own values first.
After configuring Claude Desktop and restarting it, the tool list should include market_data_get_quote and technical_get_rsi_analysis; sending "Get a quote for AAPL" and receiving price data confirms the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
MaverickMCP is a FastMCP-based local stock analysis server designed for individual traders and investors. Core tools require no API key and get market data from yfinance. It provides 37 core tools covering market data, technical analysis, stock screening, portfolio management (with risk dashboard, watchlists, and trade journal). Optional extras add backtesting (VectorBT-powered) and deep research (LangGraph-based, bring-your-own LLM key). Supports stdio and streamable HTTP transports, integrating seamlessly with Claude Desktop, Cursor, Claude Code, and Windsurf.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision 475899c4363a Data synced 2026-10-12 Read the FMRS scoring method