Skip to main content
Glama
Tickerbot MCP Server

Tickerbot MCP Server

Official
by tickerbot

tickerbot_query_news

Query news articles by ticker, keyword, or SQL filters and return per-ticker relevance and sentiment scores, plus grouped rollups for aggregated views.

Instructions

Queries news with SQL for any ticker or a screen's matches: articles with how each one treats every ticker it mentions, or rollups when you group them. ticker (one or a comma list) keeps articles that mention it; add min_relevance: 0.8 to keep only articles about it. Each article carries mentions: per ticker, relevance and sentiment_score/sentiment. Naming ticker, relevance, sentiment_score or sentiment in q/select/group_by gives one row per article per mention: q: ticker = 'NVDA' AND sentiment_score < -0.3 is articles negative about NVDA. search is full-text over title and summary. Rollups with group_by/having return truncated: true instead of paging.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tickerbot_query_news"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWHERE clause over news articles. Max 4000 chars. Required unless `search`, `ticker`, `universe`, `from` or `to` is present. Takes every article field under Returns except `mentions`, plus the per-mention fields `ticker`, `relevance`, `sentiment_score` and `sentiment` (one article per mention).
toNoArticles strictly before this instant, in the same strict ISO subset as `from` (as on `/v2/events`). A bare `YYYY-MM-DD` means through the end of that day (the ET calendar day), so `from` and `to` on the same date return that day.
dirNoSort direction. Values: asc: Ascending: smallest or earliest first. desc: Descending: largest or most recent first.desc
fromNoEarliest `time_published` (inclusive), in strict ISO: `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM[:SS]Z`. A bare date starts at 00:00 ET that day.
limitNoPage size (articles) / max groups (a `group_by` rollup). Articles take up to 1000 until 2027-01-12, then 100, and page the rest with `next_cursor`. A rollup does not page: it returns up to `limit` groups, every group up to 1000 by default, and sets `truncated: true` when there are more. A larger value is clamped to the max, not an error; see Deprecations.
orderNoSort by a bare field name or SELECT alias only (put expressions in `select` and order by their alias). Defaults to `time_published` (articles) or `volume` (rollups; with your own `select` that has no `volume` column, its last column's alias).
cursorNoFrom a prior response's `next_cursor`. Send it with the same params as the first page (`limit` may change). It holds the position and pins the read: a page whose params differ from the first page's, or a cursor sent alone, is a 400 naming the param to send.
havingNoOnly with `group_by`. HAVING clause on the rollup (max 1000 chars).
searchNoFull-text search over `title` + `summary`, in websearch grammar: `nvidia earnings` (all words), `"price target"` (phrase), `chips OR semiconductors`, `-crypto` (negation). Max 200 chars. ANDs with `q` and the other filters. Language-stemmed English.
selectNoFields or expressions to return (max 2000 chars). Defaults to the article row (no `group_by`) or `<group_by keys>, COUNT(*) AS volume` (with `group_by`). `*` returns every article field under Returns plus `mentions` (on a per-mention row, the mention's four fields too). `mentions` is selectable on its own.
tickerNoOne ticker or a comma list (up to 50): articles that mention any of them. Not combinable with `universe`. Per-mention rows still list every ticker an article mentions; put `ticker = 'NVDA'` in `q` for one ticker's rows.
group_byNoComma-separated group keys, 1-6 (max 1000 chars); the response becomes rollups. `ticker` rolls up per ticker mentioned. Name a key with `AS` to choose its JSON key; an un-named expression is named for you.
universeNoScope to a built-in universe (`top_10`, `top_100`) or one of your own, by id. An unknown one answers 200 with no results and its id in `not_found`. Articles that mention any member. Not combinable with `ticker`.
min_relevanceNoOnly with `ticker` or `universe`. Keeps an article only when it is about one of the tickers, meaning that ticker's `relevance` (0 to 1) is at least this value. `0.8` drops passing mentions. Omitted: every article that mentions them. `400` without a ticker scope; in `q`, filter the mention itself: `ticker = 'NVDA' AND relevance >= 0.8`.

Output Schema

NameRequiredDescriptionDefault
as_ofYesServer time this response was assembled (ISO 8601); on an as-of read, the instant you asked for (As-of).
countYesThe rows in `results` on this page: articles, one row per mention on a per-mention read, or groups on a rollup.
queryYesYour request echoed, each param with its effective value, in the documented param order. `ticker` is the ticker scope as a list. A param you did not send is `null`.
resultsYesArticles (one per article per mention when you name a per-mention field), or rollups when you passed `group_by`.
not_foundNoWith `ticker` or `universe`: what you named that does not exist: the symbols we do not track, in request order, or an unknown `universe` id; an empty array when every one was found. A typo here is listed, not read as "no news".
truncatedNoRollups only (`group_by`): `true` when `limit` cut the group list.
_advisoriesNoPresent only when the response carried a warning: `deprecated` (since, sunset_on, successor, warning; on a deprecated tool, successor names the tool to call), `rate_limit` (warning, retry_after_seconds, limit, remaining, reset_epoch_s) or `monthly_quota` (warning, limit, remaining, reset_epoch_s).
next_cursorYesOpaque token for the next page; `null` on the last page. Pass it back as `cursor` with the same params. Rollups do not page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.1

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers the two behaviors an agent would otherwise get wrong: naming `ticker`/`relevance`/`sentiment_score`/`sentiment` produces one row per article per mention, and rollups with group_by/having return `truncated: true` instead of paging. It omits auth/permission needs and rate limits, keeping it below a 5.

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?

Purpose is front-loaded in the first clause and the remaining sentences are dense with operational detail rather than filler. It is long in absolute terms, but justified by 14 parameters and non-obvious row-shape semantics; the schema-level duplication is the only waste.

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

Completeness4/5

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

An output schema exists, so the description correctly offloads return-field details ('every article field under Returns') instead of restating them. It covers the complex parts an agent must know — filtering, per-mention row expansion, grouping, truncation vs. paging — leaving only permissions and error-handling unaddressed.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description does add cross-parameter meaning the schema fragments cannot (the per-mention row switch, the `min_relevance`-vs-`q` equivalence, `ticker`/`universe` exclusivity is echoed rather than added), but a lot of it restates what the already-exhaustive schema documents.

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 concrete verb+resource statement: 'Queries news with SQL for any ticker or a screen's matches', and immediately clarifies the two output shapes (per-article mentions vs. group rollups). It does not distinguish itself from the sibling tickerbot_search_news, which is the most likely confusion point, so it stops short of a 5.

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

Usage Guidelines3/5

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

There is genuine in-tool guidance — use `ticker` to keep mentioning articles, add `min_relevance: 0.8` to drop passing mentions, put `ticker = 'NVDA'` in `q` for one ticker's rows — but all of it is about choosing among parameters, not about when to pick this tool over `tickerbot_search_news` or `tickerbot_query_events`. Usage is implied by scope rather than stated as exclusions or alternatives.

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