Finviz + SEC EDGAR MCP Server

screen_stocks

Screen stocks using Finviz filter codes to find investment candidates. Returns a filtered list with selected metric columns for valuation, financial, or technical analysis.

Instructions

Screen stocks using Finviz filter codes. Primary tool for finding investment candidates. Uses Finviz current snapshot data (~15-20 min delayed). Returns a filtered list with the metric columns selected by the 'table' parameter. Use list_filter_options to discover all valid filter codes.

Args: filters: Comma-separated Finviz filter codes. VALUE INVESTING EXAMPLES: "cap_largeover,fa_pe_u20,fa_roe_o15" → Large cap, P/E < 20, ROE > 15% "fa_pb_u2,fa_curratio_o1.5,fa_debteq_u0.5" → P/B < 2, current ratio > 1.5, debt/equity < 0.5 "fa_div_o3,fa_payoutratio_u60,fa_roe_o15" → Dividend > 3%, payout < 60%, ROE > 15% "fa_pfcf_u15,fa_opermargin_o15,fa_epsyoy1_o10" → P/FCF < 15, op margin > 15%, EPS growth > 10%

    USE TOOL: list_filter_options TO SEE ALL FILTERS 
    
    COMMON FILTER PREFIXES:
      cap_     : Market cap (nano/micro/small/mid/large/mega)
      fa_pe    : P/E ratio (u = under, o = over)
      fa_fpe   : Forward P/E
      fa_peg   : PEG ratio
      fa_ps    : Price/Sales
      fa_pb    : Price/Book
      fa_pc    : Price/Cash
      fa_pfcf  : Price/Free Cash Flow
      fa_roe   : Return on equity
      fa_roa   : Return on assets
      fa_roi   : Return on investment
      fa_curratio  : Current ratio
      fa_quickratio: Quick ratio
      fa_debteq    : Debt/Equity
      fa_ltdebteq  : Long-term Debt/Equity
      fa_grossmargin : Gross margin
      fa_opermargin  : Operating margin
      fa_netmargin   : Net profit margin
      fa_div   : Dividend yield
      fa_epsyoy5     : EPS growth past 5 years
      fa_salesqoq    : Sales growth QoQ
      sec_     : Sector (technology, healthcare, etc.)
      ind_     : Industry
      sh_avgvol: Average volume
      ta_sma200: Price vs 200-day SMA

table: Data view that controls which columns are returned.
       Each view returns different metrics per stock:

       "Overview" — Company, Sector, Industry, Market Cap, P/E,
           Price, Change, Volume
       "Valuation" — Market Cap, P/E, Fwd P/E, PEG, P/S, P/B,
           P/C, P/FCF, EPS This Y, EPS Next Y, EPS Past 5Y,
           EPS Next 5Y, Sales Past 5Y, Price, Change, Volume
       "Financial" — Market Cap, Dividend, ROA, ROE, ROI,
           Curr R (Current Ratio), Quick R, LTDebt/Eq, Debt/Eq,
           Gross M, Oper M, Profit M, Earnings, Price, Change, Volume
       "Ownership" — Market Cap, Outstanding, Float, Insider Own,
           Insider Trans, Inst Own, Inst Trans, Float Short,
           Short Ratio, Avg Volume, Price, Change, Volume
       "Performance" — Perf Week, Perf Month, Perf Quart,
           Perf Half, Perf Year, Perf YTD, Volatility W,
           Volatility M, Recom, Avg Volume, Rel Volume,
           Price, Change, Volume
       "Technical" — Beta, ATR, SMA20, SMA50, SMA200,
           52W High, 52W Low, RSI, Price, Change, Volume

       Use "Valuation" for value metrics, "Financial" for margins/ROE.
order: Sort column. Prefix with '-' for descending.
       e.g. "-marketcap", "pe", "-dividendyield"
signal: Optional Finviz signal preset, e.g. "ta_topgainers".
max_results: Max stocks to return (default 30).

Returns: Formatted screening results with key metrics.

Input Schema

TableJSON Schema

Name	Required	Default
`order`	No	-marketcap
`table`	No	Valuation
`signal`	No
`filters`	Yes
`max_results`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Sep 25, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does well by disclosing the ~15-20 min delayed Finviz snapshot data source and that results are a filtered list with columns determined by the table parameter. It also enumerates exact columns per table view. It does not mention rate limits or error behavior, but for a read-only screening tool the key behavioral traits are covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but organized into labeled sections (examples, prefixes, table views) and front-loaded with purpose. Some redundancy exists, such as the final 'Returns' line and the repeated instruction to use list_filter_options, but the length is largely justified by the parameter complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All five parameters are documented with examples and defaults, the data source and delay are stated, and an output schema exists so return-value detail is not required. The only gap is sibling-tool selection guidance, which is more a usage-guidelines issue than a completeness issue for invoking the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does thoroughly. Filters are explained with value-investing examples and a prefix reference; table lists all six views with their columns; order and signal get examples; max_results gets a default. This goes far beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Screen stocks using Finviz filter codes' and positions itself as the primary tool for finding investment candidates. It clearly separates itself from list_filter_options, but does not explicitly differentiate from sibling screen_value_stocks or screen_from_url, so it stops short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives actionable context: use list_filter_options to discover filter codes, and choose 'Valuation' for value metrics or 'Financial' for margins/ROE. It does not state when to prefer screen_value_stocks or screen_from_url over this tool, so exclusions are missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.