Bypassing Document Ingestion: An MCP Approach to Financial Q&A

TL;DR

This paper explores using a Model Context Protocol (MCP) for financial question answering, enabling direct data interaction with large language models, which improves accuracy for quantitative questions over traditional document retrieval methods.

Contribution

It introduces a novel MCP-based approach for financial QA, demonstrating its effectiveness and limitations compared to retrieval-augmented generation (RAG).

Findings

Achieves up to 80.4% accuracy on multi-step numerical questions.

Performs well on quantitative questions with relevant data.

Less effective for qualitative or document-specific questions.

Abstract

Answering financial questions is often treated as an information retrieval problem. In practice, however, much of the relevant information is already available in curated vendor systems, especially for quantitative analysis. We study whether, and under which conditions, Model Context Protocol (MCP) offers a more reliable alternative to standard retrieval-augmented generation (RAG) by allowing large language models (LLMs) to interact directly with data rather than relying on document ingestion and chunk retrieval. We test this by building a custom MCP server that exposes LSEG APIs as tools and evaluating it on the FinDER benchmark. The approach performs particularly well on the Financials subset, achieving up to 80.4% accuracy on multi-step numerical questions when relevant context is retrieved. The paper thus provides both a baseline for MCP-based financial question answering (QA) and evidence on where this approach breaks down, such as for questions requiring qualitative or document-specific context. Overall, direct access to curated data is a lightweight and effective alternative to document-centric RAG for quantitative financial QA, but not a substitute for all financial QA tasks.