Yahoo Finance MCP Server

screen_stocks

Read-only

Run predefined Yahoo Finance screeners to discover stocks, ETFs, or funds by movers, volume, valuation, and performance; get matching symbols with price, change, market cap, P/E, and 52-week range.

Instructions

Run one of Yahoo Finance's predefined screeners and return the matching symbols with price, % change, volume relative to the 3-month average, market cap, trailing and forward P/E, and 52-week range.

Use to discover candidates you don't have yet: today's movers, unusual volume, heavily shorted names, undervalued growth or large caps, or top ETFs and funds. Not for a symbol you already know (use get_stock_quote) and not for custom filters: only Yahoo's predefined screeners exist, so pick the closest one. Results are live and reorder through the trading day, so two calls minutes apart can differ. count takes the top N in the screener's own ranking; there is no paging. Follow up on a symbol with get_stock_quote, get_company_info or get_earnings.

Returns Markdown by default, or JSON when response_format='json'.

Input Schema

Name	Required	Description	Default
`count`	No	Number of results (1-100)
`screener`	Yes	Predefined Yahoo screener. Stocks: day_gainers, day_losers, most_actives, most_shorted_stocks, small_cap_gainers, aggressive_small_caps, growth_technology_stocks, undervalued_growth_stocks, undervalued_large_caps. ETFs: top_etfs_us, top_performing_etfs, technology_etfs, bond_etfs. Mutual funds: top_mutual_funds, solid_large_growth_funds, solid_midcap_growth_funds, conservative_foreign_funds, high_yield_bond, portfolio_anchors.
`response_format`	No	Output format: 'markdown' for human-readable or 'json' for machine-readable	markdown

Output Schema

Name	Required	Description
`count`	No
`title`	No
`total`	No
`message`	No	Set instead of data when there is nothing to return for this request (for example, no dividends on record).
`results`	No
`screener`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.6.0Nov 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the annotations, the description discloses that results are live, reorder through the trading day, and can differ between calls minutes apart, which explains the non-idempotent behavior. It also notes that count returns the top N in the screener's own ranking with no paging, and that output is Markdown by default or JSON when requested.

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

Conciseness5/5

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

The description is front-loaded with the core action and return fields, then moves into usage guidance, limitations, and follow-ups. Every sentence contributes useful selection or invocation context without unnecessary repetition.

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?

Given the output schema, annotations, and fully described parameters, the description is complete enough for an agent to choose and invoke the tool correctly. It covers purpose, alternatives, live-data behavior, ranking semantics, lack of paging, and response format.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning by explaining that count takes the top N in the screener's ranking with no paging. It also reinforces that screener must be one of Yahoo's predefined screeners and that response_format controls Markdown versus JSON output.

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

Purpose5/5

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

The description states a specific verb and resource: run Yahoo Finance's predefined screeners and return matching symbols with named data fields. It clearly distinguishes this discovery tool from get_stock_quote for known symbols and explains that custom filters are not available.

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

Usage Guidelines5/5

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

It gives explicit when-to-use guidance such as discovering movers, unusual volume, shorted names, undervalued stocks, ETFs, and funds. It also states when not to use it, naming get_stock_quote for known symbols and ruling out custom filters, plus follow-up tools for deeper research.

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

Deploy Server