Stocklake — AI Stock Intelligence

Get Market News Feed

get_news_feed

Read-onlyIdempotent

Top AI-flagged news across all tracked stocks — the market-wide news briefing. Unlike get_stock_news (per-symbol), this scans the entire universe and returns the most notable articles ranked by signal_score, newest first within each score tier.

Use this for:

Morning briefing: "what happened in the market this week?"
Catalyst scanning: "what news is driving moves right now?"
Event monitoring: "which stocks have high-impact news today?"
min_signal_score: minimum signal_score (0-100, default 60) used to SELECT articles server-side. Resolved per-article (stored/computed magnitude preferred over an unfiltered Mongo $gte, since a formal live signal doesn't exist for every article — see signal_score below), then filtered/sorted in Python.
days: look-back window in days (default 3, max 10)
limit: max articles returned (default 10, max 25)
Per article: symbol, title, published_at, ai_sentiment, ai_summary (full text), signal_score (0-100), signal_score_band (Weak/Moderate/Strong/ Very Strong)

signal_score/signal_score_band: this symbol's LIVE signal score if a news-sourced signal was raised for it in the last 90 days (same number get_stock_news()/get_signals() report, kept in sync as that signal is re-scored — one $in query per distinct symbol in the result, not per article, so two articles about the same stock always show the same value); otherwise a per-article magnitude computed from THIS article's own sentiment/confidence/flag_score, so every article still gets a real, rankable number. Always a single number — for a symbol whose live signal is genuinely two-sided (real opposing bull/bear theses), this is the STRONGER of the two sides, same as get_signals()/get_stock_news(). There is deliberately no separate "news_score" field — one name for "how strong is this idea," whether it's backed by a formal signal or just this article's own classification.

Pro tier only — AI pipeline cost attached. For informational purposes only. Not financial advice.

Input Schema

TableJSON Schema

Name	Required	Description
`days`	No	Look-back window in days (default 3, max 10).
`limit`	No	Max articles returned (default 10, max 25).
`min_signal_score`	No	Minimum signal_score used to SELECT articles server-side, 0-100 (default 60). Resolved per-article (this symbol's live signal_score if one exists, else a per-article magnitude computed from sentiment/confidence/flag_score) since a live signal doesn't exist for every article.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.9/5.0

Behavior5/5

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) already signal safety, and the description adds extensive behavioral context: how signal_score is resolved (live vs per-article), the per-symbol query optimization, the two-sided signal handling, and the lack of a separate 'news_score' field. This goes far beyond annotation hints and is highly informative.

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?

Though long, the description is well-structured: purpose, usage bullets, parameter details, output fields, scoring explanation, and restrictions. Every section provides necessary information without redundancy. The complex signal_score logic is essential and justified.

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?

The description covers everything an agent needs: what is returned, how parameters are resolved, the ranking method, the performance note (one $in query per symbol), the tier restriction, and a disclaimer. No critical details are missing given the tool's complexity.

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. The description adds meaningful nuance for min_signal_score, explaining the per-article resolution logic and why it's needed. For days and limit, it only repeats schema info, but the extra for min_signal_score justifies a 4.

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 clearly states the tool's function: 'Top AI-flagged news across all tracked stocks'. It explicitly differentiates from sibling get_stock_news ('Unlike get_stock_news (per-symbol)'), making the purpose unambiguous and distinguishing it from similar tools.

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?

The description gives concrete use cases ('Morning briefing', 'Catalyst scanning', 'Event monitoring') and contrast with get_stock_news, which implicitly tells when not to use it. It also notes the Pro tier cost, guiding the agent on when the tool is appropriate.

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

All Stocklake — AI Stock Intelligence tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation4/5

Most tools have clearly distinct targets—single stock, batch, news, history, insider activity, screener, market pulse, and so on. The closest pairs are get_earnings_calendar vs get_earnings_intelligence and get_market_assessment vs get_market_pulse, which overlap in raw inputs but differ in AI interpretation; the descriptions provide enough clarification to avoid serious misselection.

Naming Consistency5/5

All 17 tools follow a consistent get_<resource> snake_case pattern, with hierarchical names like get_stock, get_stocks, get_stock_news, get_stock_history, and get_stock_research making related resources obvious. There are no mixed naming conventions or vague verb choices.

Tool Count4/5

At 17 tools, the set is slightly above the ideal range, but the scope is broad and each tool has a plausible role in an AI stock intelligence workflow. The convenience aggregations like get_stocks and get_stock_research add some redundancy but remain purposeful rather than bloated.

Completeness5/5

The surface is comprehensive for a read-only AI stock intelligence domain: single-stock fundamentals and technicals, batch lookups, price history, per-stock and market-wide news, insider activity, screening, market pulse, macro assessment, sector intelligence, earnings, signals, and watchlist enrichment. No major operational dead ends are apparent.

Resources

Need Help?