Enables interaction with the SQLite database storing generated synthetic stock pricing data, allowing queries and management of stock price records.
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., "@sqlite-mcp-server show me the latest stock prices for apple and microsoft"
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.
Generate synthetic stock pricing data for backtesting models.
This project generates realistic synthetic stock pricing data for testing and validating stock price forecasting models. The generated data mimics real-world stock price movements with appropriate price ranges and trading dates.
Related MCP server: mcp-sqlite3
Stocks: apple, microsoft, meta, google
Exchanges: nyse, nasdaq
Price Range: $100 - $1000
Date Range: Configurable via CLI (default: last 90 days)
Output: SQLite database (stocks.db)
uv run python generate_pricing.py
# Custom date range
uv run python generate_pricing.py --start 2026-01-01 --end 2026-04-25CREATE TABLE stock_pricing (
id INTEGER PRIMARY KEY,
stock_name TEXT NOT NULL,
stock_price REAL NOT NULL,
date TEXT NOT NULL,
stock_exchange TEXT NOT NULL
);Python 3.x
uv
uv run pytest test_generate_pricing.py -vThe MCP server is now running over STDIO for direct interaction with SQLite.
uv run mcp_server.pyMIT
Get the structure of a specified table.
Inputs: table (required), db_path (required). Returns: result
List all tables in the database.
Inputs: db_path (required). Returns: result
Execute a SELECT query on the database.
Inputs: sql (required), db_path (required), params. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 3 tools
Each tool targets a distinct concern: executing SELECT queries, listing tables, and inspecting a table's schema. There is no meaningful overlap or ambiguity between them.
list_tables and get_table_structure follow a clear verb_noun pattern, but query_execution uses a noun-form name instead. The deviation is minor and the names remain understandable.
Three tools are well-scoped for a focused SQLite read-only server: a query execution entry point, table enumeration, and schema inspection. Each tool earns its place.
The set covers read-only database exploration well, but it lacks write or data-modification operations such as INSERT, UPDATE, DELETE, or DDL statements. This is a notable gap for a general SQLite server, though acceptable for read-only use cases.
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
UN FAOSTAT global food & agriculture statistics over a local SQLite mirror, via MCP.
Historical tick, order book and settlement data for Polymarket and Predict.fun crypto up/down markets, plus smart-money lists and backtest quotes, over a read-only MCP server.
Trading MCP server for AI agents, with live market data, account reads and controlled execution.
