Historical Ohlcv Time Series Retrieval With Interval Selection

via “historical ohlcv time-series retrieval with configurable intervals”

** - Interact with [Twelve Data](https://twelvedata.com) APIs to access real-time and historical financial market data for your AI agents.

Unique: Exposes Twelve Data's multi-interval historical API through MCP, allowing agents to request specific date ranges and timeframes without managing pagination or API rate limits manually; abstracts away subscription-tier differences in data availability

vs others: More flexible than static data exports because agents can request arbitrary date ranges on-demand; more cost-efficient than calling raw APIs repeatedly because MCP caching can reduce redundant requests

via “historical ohlcv time-series retrieval with interval selection”

MCP server: yfinance-mcp-server2

Unique: Parameterizes yfinance's interval selection (daily/weekly/monthly) as MCP tool arguments, allowing agents to dynamically request different granularities without code changes; converts pandas DataFrames to JSON with explicit timestamp normalization for agent consumption

vs others: More flexible than fixed-interval endpoints; avoids agents needing to manage pandas or numpy dependencies directly

via “historical stock price data retrieval with date range filtering”

MCP server: yahoo-finance-mcp

Unique: Integrates historical data retrieval as an MCP tool, allowing agents to autonomously fetch and analyze multi-year price histories without requiring manual data downloads or external data pipeline setup. Abstracts pagination and date validation logic within the MCP server.

vs others: Faster agent iteration than manual CSV imports or direct API calls — agents can request historical data inline during reasoning, enabling dynamic analysis without context switching to external tools.

via “historical ohlcv data aggregation with configurable time intervals”

MCP server: yfinance-mcp-server

Unique: Exposes yfinance's pandas-based resampling as an MCP tool, allowing agents to request pre-aggregated historical data without managing DataFrame transformations themselves. Automatically handles timezone normalization and market calendar adjustments.

vs others: More flexible than static CSV exports because agents can request arbitrary date ranges and intervals on-demand; more accessible than raw yfinance because MCP abstracts pandas/numpy complexity into simple JSON responses.