FinResearch MCP
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., "@FinResearch MCP Analyze Apple's financial health for the last 5 years"
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.
FinResearch MCP
FinResearch MCP is a production-oriented Model Context Protocol server for SEC EDGAR Company Facts research, financial analysis, valuation, and plot-ready data. It is designed as a transparent foundation for AI-assisted equity research—not as investment advice.
Highlights
Reusable, rate-limited SEC client with timeouts, transient retries, response validation, and a five-minute in-memory Company Facts cache.
Normalized annual financial histories for income statement, cash-flow, and balance-sheet metrics.
Profitability, liquidity, leverage, efficiency, and cash-conversion ratios.
Assumption-driven CAPM, WACC, DCF, enterprise value, equity value, intrinsic value, and sensitivity analysis tools.
High-level company analysis, peer comparison, and structured chart data.
Provider-neutral RAG contracts for future 10-K/10-Q, MD&A, and risk-factor retrieval.
Related MCP server: SEC EDGAR MCP Server
Installation and usage
Requirements: Python 3.12+, uv, and a contact email address for SEC requests.
uv sync
uv run mcp dev main.pymcp dev main.py launches MCP Inspector. The exported main:mcp object also
works with stdio-based MCP clients. Set FINRESEARCH_LOG_LEVEL=DEBUG for
diagnostic logs; logs use stderr so MCP stdio remains clean.
Tools
Area | Tools |
Existing tools |
|
Financial data |
|
Analysis |
|
Valuation |
|
Version 2 platform |
|
get_company_financials covers revenue, revenue history, net income,
operating income/EBIT, gross profit, EBITDA when depreciation data is reported,
EPS, diluted EPS, operating cash flow, free cash flow, CapEx, cash, debt,
current assets/liabilities, total assets/liabilities, equity, and book value.
Market capitalization and market-derived enterprise value are explicitly null
because SEC Company Facts is not a market-data service.
Data and calculation notes
Annual duration facts are 10-K records between 330 and 380 days; when a period has multiple filings, the most recently filed observation is used.
Instant balance-sheet facts use their latest 10-K period end.
Unreported or non-standard company concepts return
null; the server does not fabricate estimates.Ratio calculations use reported latest values. ROIC assumes a 21% tax rate where tax expense is not consistently available.
DCF tools require explicit assumptions and return structured intermediate projections for auditability.
Development
.venv/bin/python -m compileall -q main.py clients models rag tools utils tests
.venv/bin/python -m unittest discover -s tests -vThe tests use mocked HTTP transports and never call SEC EDGAR. See architecture documentation, RAG preparation, and example prompts. See Version 2 platform documentation for filing RAG, market-data limitations, dashboard payloads, portfolios, and report exports.
Folder structure
clients/ SEC API integration
models/ typed financial domain models
tools/ MCP tool groups
utils/ extraction, ratios, valuation, logging, constants
rag/ future filing-retrieval interfaces
tests/ offline unit tests
docs/ architecture and RAG design
examples/ prompts for MCP clientsAvailable Tools
24 toolsai_analyze_companyC
Generate an attributable AI-ready research brief from financials and indexed filings.
Inputs: cik (required), contact_email (required), filing_query. Returns: object
analyze_companyC
Generate a comprehensive, deterministic financial-health analysis from SEC data.
Inputs: cik (required), contact_email (required), years. Returns: object
analyze_portfolioB
Analyze position weights, market value, unrealized return, and concentration.
Inputs: positions (required). Returns: object
calculate_cagrC
Calculate compound annual growth rate (CAGR) as a percentage.
Inputs: years (required), ending_value (required), beginning_value (required). Returns: result
calculate_capm_cost_of_equityB
Calculate CAPM cost of equity as a decimal rate.
Inputs: beta (required), risk_free_rate (required), expected_market_return (required). Returns: result
calculate_dcf_valuationC
Calculate enterprise value with a constant-growth discounted cash flow model.
Inputs: growth_rate (required), discount_rate (required), free_cash_flow (required), terminal_growth_rate (required), +1 more. Returns: object
calculate_enterprise_valueA
Calculate enterprise value from market capitalization, debt, and cash.
Inputs: cash (required), debt (required), market_cap (required). Returns: result
calculate_equity_value_from_enterprise_valueB
Calculate equity value from enterprise value, cash, and debt.
Inputs: cash (required), debt (required), enterprise_value (required). Returns: result
calculate_wacc_rateB
Calculate WACC as a decimal rate from market-value capital weights.
Inputs: tax_rate (required), cost_of_debt (required), cost_of_equity (required), market_value_debt (required), +1 more. Returns: result
compare_companiesC
Compare revenue, margins, returns, cash flow, debt, growth, and valuation availability.
Inputs: first_cik (required), second_cik (required), contact_email (required). Returns: object
export_company_report_markdownC
Create a Markdown company research report at a relative project path.
Inputs: cik (required), contact_email (required), output_path. Returns: object
export_company_report_pdfC
Create a PDF company research report at a relative project path.
Inputs: cik (required), contact_email (required), output_path. Returns: object
get_company_chart_dataC
Return structured revenue, income, cash-flow, debt, and growth data for plotting.
Inputs: cik (required), contact_email (required), years. Returns: object
get_company_financialsC
Return supported annual financial metrics and plot-ready histories for a company.
Inputs: cik (required), contact_email (required), years. Returns: object
get_dashboard_dataB
Aggregate company analysis, financial trends, and optional market data for a dashboard.
Inputs: cik (required), contact_email (required), years, ticker. Returns: object
get_financial_factC
Retrieve annual US-GAAP financial history from SEC EDGAR.
Inputs: cik (required), concept (required), contact_email (required), unit, +1 more. Returns: object
get_financial_ratiosC
Calculate profitability, liquidity, leverage, and efficiency ratios from SEC data.
Inputs: cik (required), contact_email (required). Returns: object
get_market_price_historyB
Return delayed plot-ready market OHLCV history for a ticker.
Inputs: ticker (required), range, interval. Returns: result
get_market_snapshotA
Return delayed public market-price metadata for a ticker.
Inputs: ticker (required). Returns: object
get_sec_company_factsC
Retrieve XBRL company facts metadata from SEC EDGAR.
Inputs: cik (required), contact_email (required). Returns: object
index_sec_filingB
Fetch, chunk, and index a known SEC filing document for RAG retrieval.
Inputs: cik (required), form_type (required), filing_date (required), contact_email (required), +3 more. Returns: object
run_dcf_sensitivity_analysisB
Return a structured DCF sensitivity grid for charting or tabulation.
Inputs: growth_rate (required), discount_rates (required), free_cash_flow (required), terminal_growth_rates (required), +1 more. Returns: result
search_sec_filing_ragC
Search locally indexed SEC filing chunks with attributable lexical retrieval.
Inputs: cik (required), query (required), limit. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 24 tools
Most tools have distinct purposes (e.g., calculate_cagr vs calculate_dcf_valuation), but some overlap exists: get_financial_fact, get_company_financials, and get_sec_company_facts all retrieve SEC financial data, and analyze_company, ai_analyze_company, and get_dashboard_data produce overlapping analytical outputs. Descriptions help but boundaries could be clearer.
All tool names follow a consistent verb_noun pattern in snake_case (calculate_*, get_*, run_*, analyze_*, compare_*, index_*, search_*, export_*). There are minor prefixes like 'ai_' and suffixes like '_rag', but they are applied consistently and do not break the overall convention.
With 24 tools, the server is on the high end of the typical range, but the count is justified by the comprehensive scope covering financial data retrieval, ratio analysis, valuation models, portfolio analytics, market data, reporting, and RAG-based search. Each tool addresses a distinct need, though the set could be slightly consolidated.
The tool surface covers the full financial research workflow: fetching SEC data, calculating metrics and valuations, running sensitivity analysis, comparing companies, analyzing portfolios, retrieving market data, and exporting reports. Missing a direct tool for listing filings or comparing against industry benchmarks, but these are minor gaps that can be worked around with existing tools.
Related MCP Connectors
Provide AI assistants with real-time access to official SEC EDGAR filings and financial data. Enab…
Search SEC EDGAR filings, financial statements, and company data.
SEC-filed company financials with filing citations, plus market data, for AI agents
SEC EDGAR financials, insider trading, and economic data for AI agents. US GAAP + IFRS.
Related MCP Servers
AlicenseAqualityDmaintenanceEnables AI clients to search and analyze SEC filings, financial statements, insider trades, and institutional holdings through natural language tools.96 npm1MIT- FlicenseNot gradedqualityDmaintenanceEnables to search and retrieve SEC EDGAR filings, insider transactions, major shareholders, and executive compensation data through natural language.-
- AlicenseNot gradedqualityCmaintenanceEnables querying of SEC EDGAR filings and financial data via natural language, offering tools for company lookup, filing retrieval, XBRL data, and full-text search.146 npmMIT
- AlicenseAqualityBmaintenanceAn MCP server for SEC EDGAR written in Rust: company filings, full-text search, XBRL financials, insider transactions and company info. A single native binary; no API key.3214MIT