StockFit API

StockFit API is a revolutionary financial data platform engineered for the next generation of quantitative analysis, algorithmic trading, and AI-driven research. It obliterates the traditional tradeoffs that have long plagued developers, quants, and research platforms: the painful choice between cheap, inaccurate data tiers and prohibitively expensive enterprise contracts. StockFit delivers direct, unfiltered access to SEC filing data, pulling every fact, figure, and footnote straight from the source. This is not a derived, processed, or sanitized middle layer; every single number is traceable back to its original SEC XBRL filing, ensuring absolute integrity and auditability. The platform is built for real-world financial modeling and backtesting, handling the complexities that break lesser APIs. It correctly processes amended filings, computes non-December fiscal year ends with precision, and reconstructs Q4 data from the interplay of 10-K and 10-Q reports. Beyond raw fundamentals, StockFit provides rich, AI-friendly economic models for each company, covering offerings, competitive advantages, strategic initiatives, and failure modes. For ETF and mutual fund exposure, it offers deep models on mandate, portfolio construction, costs, and sensitivities, all optimized for Large Language Model (LLM) workflows. With over 250 million facts across 5 million filings, updated daily, StockFit is the definitive, future-proof data source for anyone serious about modeling financial reality. It comes with a standard REST API and a native MCP server, making it instantly compatible with Claude, Cursor, and other cutting-edge AI tools.

Direct SEC XBRL Data Integrity

This feature eliminates the data degradation common in aggregated financial APIs. StockFit pulls every financial fact directly from the SEC's XBRL database, bypassing any derived middle layer that introduces errors or latency. Every metric you query, from revenue to earnings per share, is a direct copy of what the company filed, complete with a source citation linking it to the specific filing accession number. This creates an unbreakable chain of custody for your data, essential for audit trails, regulatory compliance, and high-stakes quantitative research where a single erroneous decimal can lead to catastrophic modeling failures.

Advanced Fiscal Period Handling

Standard financial APIs often stumble on complex accounting realities, but StockFit is engineered to handle them all. It correctly processes amended filings, ensuring you always have the most current, restated data without manual reconciliation. The API intelligently computes data for companies with non-December fiscal year ends, a common source of error in backtesting. Furthermore, it can reconstruct Q4 financials by intelligently analyzing the relationship between annual 10-K reports and quarterly 10-Q filings, providing a complete and accurate quarterly picture that many APIs simply omit or calculate incorrectly.

Rich Economic and Exposure Models

StockFit transcends basic financial statements by providing pre-built, AI-optimized economic models for every company. These models analyze offerings, peer comparisons, operating levers, competitive advantages, business flywheels, strategic initiatives, and potential failure modes. For institutional-grade analysis, the API also provides deep ETF and mutual fund exposure models. These models detail a fund's mandate, portfolio construction methodology, cost structure, and risk sensitivities, making them instantly usable for LLM workflows and sophisticated portfolio analysis without requiring you to build the analytical framework from scratch.

Native MCP Server for AI Tools

StockFit is built for the AI-native era, featuring a native Model Context Protocol (MCP) server. This allows for seamless, zero-configuration integration with leading AI tools like Claude, Cursor, and other LLM-powered platforms. Instead of writing complex API clients or wrestling with data formatting, you can directly query financial data using natural language within your AI development environment. This dramatically accelerates research, coding, and analysis workflows, turning your AI assistant into a powerful, data-backed financial analyst that can pull real-time SEC data on command.

Automated Quantitative Backtesting

Quants and algorithmic traders can use StockFit to build and test models with the most reliable financial data available. The API's standardized financials and sector-aware metrics are structured for direct ingestion into backtesting engines. By using data that correctly handles amended filings and non-standard fiscal years, you eliminate a major source of look-ahead bias and data errors. This allows for the creation of robust, historically accurate trading strategies that can be deployed with confidence, knowing the underlying data is a perfect reflection of what was publicly available at the time.

AI-Powered Fundamental Research

Analysts and portfolio managers can leverage StockFit's rich economic models and direct data access to supercharge their research. By feeding the API's output into an LLM via the native MCP server, you can ask complex questions like "What are the primary failure modes for this company based on its competitive advantages and operating levers?" The AI will analyze the pre-built models and raw financials to provide a nuanced, source-cited answer. This transforms the research process from manual data gathering and spreadsheet analysis to a dynamic, conversational investigation of a company's financial health.

Dynamic ETF and Fund Exposure Analysis

Risk managers and asset allocators can use StockFit to gain unprecedented transparency into ETF and mutual fund holdings. The API's exposure models go beyond simple top-10 holdings, detailing a fund's mandate, portfolio construction rules, and cost sensitivities. You can model how a fund would react to specific market scenarios or sector rotations, providing a dynamic risk assessment that static fact sheets cannot offer. This is critical for constructing resilient portfolios and understanding the true, underlying risk factors in any fund investment.

LLM and AI Agent Data Pipeline

Developers building financial AI agents or chatbots can use StockFit as their primary, trusted data pipeline. The REST API and MCP server provide a clean, structured, and verifiable data source that AI models can reliably consume. Because every fact is traceable to an SEC filing, your AI agents can cite their sources, building trust and credibility with users. This enables the creation of advanced applications like automated financial report generators, intelligent portfolio advisors, and regulatory compliance bots that operate on a foundation of unassailable data integrity.

How does StockFit ensure the accuracy of its financial data?

StockFit guarantees accuracy by pulling every data point directly from the SEC's XBRL database, with no intermediate processing or data enrichment layers that can introduce errors. Every fact in the API response includes a source citation linking it to the specific SEC filing accession number. This means you can always trace a number back to its original filing for verification, ensuring the data is as authoritative as what the company itself filed.

Can StockFit handle companies with non-standard fiscal years?

Yes, this is a core feature. StockFit is built to correctly compute and present data for companies that do not have a December fiscal year end. It understands the specific reporting periods for each company and adjusts its data queries and calculations accordingly. This eliminates a common source of data mismanagement and error in financial modeling and backtesting.

What is the MCP server and how do I use it?

The MCP (Model Context Protocol) server is a native interface that allows AI tools like Claude and Cursor to directly query StockFit's data. Instead of writing code to call a REST API, you can simply ask your AI assistant a question like "Get me Apple's revenue for the last 5 fiscal years." The MCP server handles the authentication, query, and data formatting automatically, making the data instantly accessible within your AI workflow for analysis and code generation.

What types of economic models does the API provide?

StockFit provides rich, pre-built economic models for each company and for ETFs/MFs. Company models analyze offerings, peers, operating levers, competitive advantages, business flywheels, strategic initiatives, and failure modes. ETF/MF exposure models cover the fund's mandate, portfolio construction methodology, cost structure, risk sensitivities, and use cases. These models are designed to be AI-friendly, providing structured, contextual data that LLMs can easily parse and reason over.