About Bolsai
Bolsai is an MCP server that gives AI assistants access to Brazilian market data from B3, CVM, and BCB. It covers equities, FIIs, company financials, and macro indicators.
Key features
- 01Stock quotes and price history
- 02Fundamentals and financial statements
- 03Stock comparison and screening
- 04Dividends and FII details
- 05Brazilian macro indicators
Use cases
- 01Check a B3-listed stock’s current price
- 02Compare companies using financial metrics
- 03Review dividends or FII distributions
- 04Look up SELIC, IPCA, CDI, or USD/BRL
MCP support
The MCP server exposes Brazilian stock, FII, company financial, and macro data tools to MCP clients. Access requires a Bolsai API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx bolsai-mcpBOLSAI_API_KEYSecretYour bolsai API key (free tier available at usebolsai.com)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBolsai - MCP Server
Brazilian financial market data for AI assistants. Query stock prices, fundamentals, dividends, FIIs, and macro indicators from the Brazilian market (B3, CVM, BCB) directly from Claude.
Quick Start
-
Get a free API key at usebolsai.com
-
Install:
pip install bolsai-mcp
- Add to Claude Desktop (
claude_desktop_config.json):
{
"mcpServers": {
"bolsai": {
"command": "uvx",
"args": ["bolsai-mcp"],
"env": {
"BOLSAI_API_KEY": "sk_your_key_here"
}
}
}
}
Or for Claude Code (.mcp.json):
{
"mcpServers": {
"bolsai": {
"command": "bolsai-mcp",
"env": {
"BOLSAI_API_KEY": "sk_your_key_here"
}
}
}
}
Tools
| Tool | Description | Example Prompt |
|---|---|---|
get_stock_quote | Current price, daily change, 52w range | "What's PETR4 trading at?" |
get_fundamentals | 27+ indicators: P/L, P/VP, ROE, margins | "Show me VALE3 fundamentals" |
compare_stocks | Side-by-side comparison of up to 5 stocks | "Compare PETR4 vs VALE3 vs ITUB4" |
get_dividends | Dividend yield, annual summary, payments | "What dividends did BBDC4 pay?" |
search_companies | Find companies by name or sector | "Find banks listed on B3" |
get_price_history | OHLCV prices since 1986 with adjustments | "PETR4 prices last month" |
get_fii_details | FII fundamentals + distributions | "Show me HGLG11" |
get_macro_indicator | SELIC, IPCA, CDI, USD/BRL | "What's the current SELIC rate?" |
get_financial_statements | Raw CVM income/balance/cash flow | "PETR4 income statement 2024" |
screen_stocks | Filter stocks by metrics | "Find stocks with DY > 8%" |
Example Conversations
"What's PETR4 trading at?"
PETR4
Price: R$ 36.19
Change: +R$ 0.53 (+1.49%)
Date: 2024-12-30
52-week: R$ 28.44 – R$ 42.15
YTD: +12.34%
"Compare PETR4 vs VALE3"
Comparison: PETR4 vs VALE3
Metric PETR4 VALE3
─────────────────────────────────────
P/L 4.89 5.23
P/VP 1.12 1.45
EV/EBITDA 3.21 3.87
ROE 33.20% 27.70%
Net Margin 24.50% 23.10%
DY 12.30% 9.90%
Price R$ 36.19 R$ 58.42
Data Coverage
- 350+ stocks listed on B3
- 400+ FIIs (Real Estate Investment Funds)
- 40 years of price history (since 1986)
- 15+ years of fundamentals (since 2010)
- 27 indicators including P/L, P/VP, EV/EBITDA, ROE, ROIC, margins
- Macro data: SELIC, IPCA, CDI, USD/BRL
- Updated daily from official sources (B3, CVM, BCB)
Configuration
| Environment Variable | Required | Default | Description |
|---|---|---|---|
BOLSAI_API_KEY | Yes | — | API key from usebolsai.com |
BOLSAI_BASE_URL | No | https://usebolsai.com/api/v1 | API base URL |
API Tiers
- Free: 200 requests/day. Stock quotes, current fundamentals, company search.
- Pro (R$ 49/month): 10,000 requests/day. All tools including history, dividends, financials, macro.
Development
cd mcp-server
pip install -e ".[dev]"
pytest
ruff check . && ruff format .
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.