BRVM MCP Server
This MCP server gives an AI agent read-only access to live BRVM (West African stock exchange) market data through seven tools.
Market overview —
get_market_summaryreturns the day's total volume, value traded, gainer/loser counts, and all index values.Single stock quote —
get_stock_pricetakes a ticker (e.g. SNTS, SGBC, ETIT, ORAC, ONTBF) and returns price, change, volume, and company details.Indices —
get_indicesreturns BRVM Composite, BRVM 30, Prestige, Principal, and sector indices with value, change, and YTD performance.Movers —
get_top_moversreturns top N gainers and losers (default 5, max 10).Company profiles —
get_company_inforeturns name, country, sector, and market cap for a ticker.Search & discovery —
search_stocksfilters by free-text name/ticker, UEMOA country, or sector (at least one filter required);list_tickerslists all ~46 tickers with metadata.Output shape — every tool returns a JSON payload as a string; no authentication and no write operations.
Note: the README advertises two additional Sikafinance tools (get_sika_stock_page, get_sika_news) that are not present in this schema.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BRVM MCP Server show me the top gainers on BRVM today"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🇨🇮 BRVM MCP Server
An MCP server for West Africa's regional stock exchange.
Connect any AI agent — Claude, ChatGPT, Cursor, Copilot, LangGraph — to live market data from the BRVM (Bourse Régionale des Valeurs Mobilières), serving 8 UEMOA member states across West Africa.
Why?
The BRVM lists ~46 companies across Bénin, Burkina Faso, Côte d'Ivoire, Guinée-Bissau, Mali, Niger, Sénégal, and Togo, with a combined market cap of about 21 trillion XOF (brvm.org, 2026-10-14). Yet it has no public API. This server bridges that gap, making BRVM data accessible to the AI ecosystem via the Model Context Protocol.
What's coming on the BRVM
December 18, 2026: First derivatives market in francophone West Africa (futures on indices and stocks)
2026–2027: ETF listings
2026: Agricultural commodities exchange (BMPA CI) — cashew, maize, cola nut
This server is built to grow alongside these developments.
Related MCP server: Alpha Vantage MCP Server
Features
Tools (9)
Tool | Description |
| Full trading session overview: volume, value, gainers/losers, indices |
| Current quote for a specific ticker (price, change, volume) |
| All BRVM indices: Composite, BRVM 30, Prestige, Principal, sectors |
| Top N gainers and losers of the day |
| Company details: name, country, sector, market cap |
| Search by name, country, or sector |
| All ~46 BRVM tickers with metadata |
| Sikafinance page of a ticker: beta, RSI, % of capital traded, dividend history, price ranges, recent headlines, investor poll |
| Dated news headlines of a ticker, from Sikafinance |
Resources
URI | Description |
| BRVM exchange overview for context injection |
Prompts
Prompt | Description |
| Structured analysis of a BRVM stock |
| Full daily market report template |
Quick Start
Prerequisites
Python 3.11+
uv (recommended) or pip
Install & Run
# Clone
git clone https://github.com/Dilane-Kamga/brvm-mcp-server.git
cd brvm-mcp-server
# Install
uv sync
# Run (stdio — for Claude Desktop / Cursor)
uv run brvm-mcp
# Run (HTTP — for remote agents / web apps)
uv run brvm-mcp --transport streamable-http --port 8000Connect to Claude Desktop
Add to your Claude Desktop config: ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows.
{
"mcpServers": {
"brvm": {
"command": "uv",
"args": ["run", "--directory", "/path/to/brvm-mcp-server", "brvm-mcp"]
}
}
}Quit Claude Desktop completely and start it again: it reads the config only at startup. The BRVM tools then appear in the tools menu of a conversation.
Test with MCP Inspector
npx @modelcontextprotocol/inspector uv run brvm-mcpDocker (remote deployment)
docker build -t brvm-mcp .
docker run -p 8000:8000 brvm-mcpExample Conversations
Once connected, you can ask Claude:
"What's the BRVM market doing today?" → Calls
get_market_summary(), returns full session data
"Show me Sonatel's stock price" → Calls
get_stock_price("SNTS")
"What does Sikafinance show for Sonatel: RSI, beta, latest news?" → Calls
get_sika_stock_page("SNTS")
"Which BRVM stocks are from Sénégal?" → Calls
search_stocks(country="Sénégal")
"Give me a full market report" → Uses the
market_reportprompt to orchestrate multiple tool calls
"Which stocks dropped the most today?" → Calls
get_top_movers(), focuses on losers
Architecture
┌──────────────────┐ MCP (stdio/HTTP) ┌──────────────────┐
│ AI Agent │◄────────────────────────►│ BRVM MCP Server │
│ (Claude, GPT, │ │ │
│ Cursor, etc.) │ │ FastMCP + Tools │
└──────────────────┘ │ + Cache Layer │
└────────┬─────────┘
│ httpx
┌────────────────────────┴───────────────┐
┌────────▼─────────┐ ┌─────────▼────────┐
│ brvm.org │ │ sikafinance.com │
│ • Homepage (same-│ │ • Ticker pages │
│ day price/idx) │ │ (beta, RSI, │
│ • BOC PDF (volume│ │ dividends) │
│ /YTD/Principal,│ │ • News headlines │
│ 1h cache) │ │ (15 min delay) │
└──────────────────┘ └──────────────────┘FastMCP: Decorator-based MCP framework (official Python SDK)
httpx: Async HTTP client for scraping
BeautifulSoup4 + lxml: HTML parsing
pdfplumber: BOC PDF parsing (index summary regex + per-stock table extraction)
diskcache: TTL-based disk caching (5min default, respectful of sources)
Pydantic: Structured data models
Prices, indices and volumes come from the exchange's own site (brvm.org). Sikafinance adds
fields the exchange does not publish. An earlier version scraped afx.kwayisi.org as its primary
source; it lagged a full trading session and had uptime problems, so it was dropped.
Roadmap
v0.2 — Historical price data (OHLCV bars)
v0.3 — BRVM official announcements / corporate actions feed
v0.4 — BMPA CI commodities data (when available)
v0.5 — Derivatives data (futures, options — post Dec 2026 launch)
v1.0 — OAuth + rate limiting for multi-user deployment
Register on MCP Registry
Data sources and terms
Source | What it provides | Freshness |
brvm.org homepage | Prices, % change, market cap, value traded, BRVM Composite / 30 / Prestige | Same day |
Bulletin Officiel de la Cote (PDF on brvm.org) | Volume per stock, year-to-date % of the indices, BRVM Principal | One session behind |
Beta, RSI, % of capital traded, dividend history, dated headlines, investor poll | 15 minutes delayed (Sikafinance's own notice) |
This project is not affiliated with the BRVM or with Sikafinance, and the data belongs to them. The server reads public pages when a tool is called, for research and personal use; it does not host or redistribute a copy of them. brvm.org's legal notice reserves all reproduction rights, so check each source's terms before you redistribute its data.
How the server treats its sources:
robots.txt is respected: no request to a disallowed path. brvm.org's robots.txt asks for 10 seconds between requests; the cache keeps repeated tool calls off the site, so avoid calling tools in a tight loop.
Caching: 5 minutes per tool call, 1 hour for the BOC PDF.
Polite User-Agent that names the project.
Public pages only: no login and no paywall. Sikafinance's premium articles come back as headlines only.
For real-time FIX feeds, contact BRVM directly: brvm.org/real-time-data-feed
Contributing
Contributions are welcome, in English or French. Start with
CONTRIBUTING.md: setup, checks, how to add a tool, and the rules for collecting
data. Issues labelled
good first issue
are a good way in.
Priority areas:
Historical data (OHLCV bars, roadmap v0.2)
Offline tests on saved pages (VCR cassettes) for the scrapers
Additional data sources, once their terms allow it
TypeScript port for Node.js MCP hosts
If the project is useful to you, a star on GitHub helps other people find it.
Contributors
@AmadouAz: brvm.org as the primary source, with the BOC PDF (#1); Sikafinance stock pages and news (#2).
License
MIT
Built with ☕ in Mauritius by Dilane Fogué Kamga — Senior Software & AI Engineer, Financial Engineering MSc (WorldQuant University).
Bridging AI and African capital markets.
Available Tools
7 toolsget_company_infoB
Get detailed information about a BRVM-listed company.
Args: ticker: The BRVM ticker symbol.
Returns company name, country, sector, and market cap.
Inputs: ticker (required). Returns: result
get_indicesA
Get current values for all BRVM indices: BRVM Composite (BRVM-CI), BRVM 30, BRVM Prestige, BRVM Principal, and sector indices.
Returns a JSON array of index objects with value, change, and YTD performance.
Inputs: no named parameters. Returns: result
get_market_summaryA
Get today's BRVM market summary including total volume, value traded, number of gainers/losers, and all index values.
Returns a JSON object with the full trading session overview.
Inputs: no named parameters. Returns: result
get_stock_priceA
Get the current price and trading data for a specific BRVM-listed stock.
Args: ticker: The BRVM ticker symbol (e.g., SNTS for Sonatel, SGBC for Société Générale CI, ETIT for Ecobank Transnational, ORAC for Orange CI, ONTBF for Onatel).
Returns a JSON object with price, change, volume, and company details.
Inputs: ticker (required). Returns: result
get_top_moversA
Get today's top gaining and losing stocks on the BRVM.
Args: n: Number of stocks to return per category (default 5, max 10).
Returns a JSON object with 'gainers' and 'losers' arrays.
Inputs: n. Returns: result
list_tickersA
List all BRVM ticker symbols with their company names, countries, and sectors.
Useful for discovering available tickers before calling get_stock_price. Returns a JSON array of all ~46 listed companies.
Inputs: no named parameters. Returns: result
search_stocksA
Search BRVM-listed stocks by name, country, or sector.
Args: query: Free-text search on company name or ticker (e.g., 'orange', 'ecobank', 'SNTS'). country: Filter by UEMOA country (e.g., 'Sénégal', 'Côte d'Ivoire', 'Burkina Faso', 'Bénin', 'Togo', 'Mali', 'Niger', 'Guinée-Bissau'). sector: Filter by sector (e.g., 'Services Financiers', 'Agriculture', 'Services Publics', 'Industrie', 'Distribution', 'Transport').
Returns a JSON array of matching companies. At least one filter must be provided.
Inputs: query, country, sector. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct function: company info, price data, indices, market summary, movers, ticker list, and search. Minimal overlap; descriptions clarify boundaries.
All tool names follow a clear verb_noun pattern in snake_case (e.g., get_company_info, list_tickers, search_stocks), providing predictability for agents.
Seven tools cover the essential operations for a stock exchange information server without redundancy or unnecessary complexity, fitting well within the ideal 3-15 range.
The set covers core information retrieval needs (price, company details, indices, search, movers). Minor gaps like historical data or dividend info exist but do not critically impair typical workflows.
Maintenance
Related MCP Connectors
A Model Context Protocol server exposing real-time and historical Colombo Stock Exchange (CSE) data to AI agents and LLM applications. Provides quotes and OHLCV price history, full financial statements (income, balance sheet, cash flow), pre-computed technicals (moving averages, RS ratings, volume signals), macroeconomic indicators, corporate actions, and rule-based screening across CSE stocks and sector indices, everything needed to build CSE-aware trading assistants, research tools, and market-analysis agents. This is the official MCP server of www.ceyloncharts.com
Live crypto + IDX stock market intelligence for AI agents — 19 tools, no API key.
Live stock quotes, a stock screener, crypto prices and FX rates as agent tools.
Free public stock research, market context, and comparisons for AI agents.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides access to real-time stock prices, financial statements, news, and options data via the Model Context Protocol. It enables AI assistants to retrieve comprehensive market data, including historical prices and analyst recommendations, through a standardized interface.964 PyPI3MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLMs and agentic workflows to access real-time and historical stock market data through the Model Context Protocol.227MIT
- AlicenseNot gradedqualityBmaintenanceProvides structured access to Nepal Stock Exchange market data through the Model Context Protocol, enabling AI integration for querying real-time stock data and market analysis.64MIT
- FlicenseAqualityDmaintenanceEnables financial research by providing stock quotes, historical prices, RSI indicators, and AI-generated analyst reports through the Model Context Protocol.4-