mcp-server

tickerbot_search_news

SQL query over the news archive. Article rows, or rollups when you group them. Filter to a ticker with the ticker param, or in q via the auto-unnest alias tk = 'NVDA'. search is full-text over title and summary. Rollups with group_by/having return truncated: true instead of paging.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	WHERE clause over the news_article table. Max 4000 chars. Required UNLESS `search` or a scoping param (`ticker`/`tickers`/`universe`/`from`/`to`) is present — the simplest call needs no SQL. Queryable columns: `time_published`, `title`, `summary`, `source`, `source_domain`, `category`, `authors`, `topics`, `overall_sentiment_score`, `overall_sentiment_label`, `tickers`, `ticker_data`, `banner_image`, `url`, `id`, `created_at` — plus `tk`, the per-ticker UNNEST alias. Signal/state columns are not joinable here.
`to`	No	Articles strictly before this instant — same strict ISO subset, matching `/v2/events`. (`until` accepted as an alias.)
`dir`	No	Sort direction.	desc
`from`	No	Earliest `time_published` (inclusive) — strict ISO: `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM[:SS]Z`. (`since` accepted as an alias.)
`limit`	No	Page size. Max 1000.
`order`	No	Sort — a bare column name or SELECT alias only (put expressions in `select` and order by their alias). Defaults to `time_published` (article rows) or `volume` (aggregate rows).
`cursor`	No	Opaque pagination cursor from a prior response's `next_cursor`.
`having`	No	HAVING clause on the aggregate (max 1000 chars). Requires `group_by`.
`search`	No	Full-text search over `title` + `summary` — websearch grammar: `apple earnings` (all words), `"price target"` (phrase), `chips OR semiconductors`, `-crypto` (negation). Max 200 chars. ANDs with `q` and the scoping params. Language-stemmed English.
`select`	No	Columns/expressions to return (max 2000 chars). Defaults to article columns (no `group_by`) or `<group_by cols>, COUNT(*) AS volume` (with `group_by`).
`ticker`	No	Articles mentioning this symbol (ANDed with `q`).
`tickers`	No	Comma list, up to 50 — articles mentioning ANY of them. Not combinable with `ticker` or `universe`.
`group_by`	No	AGGREGATE MODE: comma-separated group keys, 1-6 (max 1000 chars). Switches the response to rollup rows. Use `tk` to roll up per ticker without writing the UNNEST. Name a key with `AS` to choose its JSON key; an un-named expression is named for you rather than returned as `?column?`.
`universe`	No	Universe slug — articles mentioning any member. Not combinable with `ticker`/`tickers`.

Output Schema

TableJSON Schema

Name	Required	Description
`as_of`	Yes	Server time this response was assembled (ISO 8601).
`count`	Yes	Rows in this page.
`query`	Yes	Your filters, echoed.
`results`	Yes	Article rows, or rollup rows when you passed `group_by`. Aggregate responses add `truncated: true` when `limit` cut the group list.
`truncated`	No	Aggregate mode only (`group_by`): `true` when the rollup stopped at its row cap.
`next_cursor`	Yes	Opaque token for the next page; `null` on the last page. Pass it back as `cursor`.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "as_of": {
+      "description": "Server time this response was assembled (ISO 8601).",
+      "type": "string"
+    },
+    "count": {
+      "description": "Rows in this page.",
+      "type": "number"
+    },
+    "next_cursor": {
+      "description": "Opaque token for the next page; `null` on the last page. Pass it back as `cursor`.",
+      "type": "string"
+    },
+    "query": {
+      "description": "Your filters, echoed.",
+      "type": "object"
+    },
+    "results": {
+      "description": "Article rows, or rollup rows when you passed `group_by`. Aggregate responses add `truncated: true` when `limit` cut the group list.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "truncated": {
+      "description": "Aggregate mode only (`group_by`): `true` when the rollup stopped at its row cap.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "as_of",
+    "query",
+    "count",
+    "next_cursor",
+    "results"
+  ],
+  "type": "object"
+}

Changed16 schema fields changedSep 17, 2026

changedInput schema / properties / cursor / description

Previous value: -"Opaque cursor."New value: +"Opaque pagination cursor from a prior response's `next_cursor`."

addedInput schema / properties / dir / default
```
Added value: +"desc"
```

addedInput schema / properties / from

Added value: +{
+  "description": "Earliest `time_published` (inclusive) — strict ISO: `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM[:SS]Z`. (`since` accepted as an alias.)",
+  "type": "string"
+}

changedInput schema / properties / group_by / description

Previous value: -"Comma-separated columns for aggregation. Alias a key with `AS` to name its JSON key; un-named expressions are named for you."New value: +"AGGREGATE MODE: comma-separated group keys, 1-6 (max 1000 chars). Switches the response to rollup rows. Use `tk` to roll up per ticker without writing the UNNEST. Name a key with `AS` to choose its JSON key; an un-named expression is named for you rather than returned as `?column?`."

changedInput schema / properties / having / description

Previous value: -"WHERE-style filter on aggregates. Requires group_by."New value: +"HAVING clause on the aggregate (max 1000 chars). Requires `group_by`."

addedInput schema / properties / limit / default
```
Added value: +50
```

changedInput schema / properties / limit / description

Previous value: -"Page size."New value: +"Page size. Max 1000."

changedInput schema / properties / order / description

Previous value: -"Sort column or SELECT alias. Default time_published (non-aggregate) or volume (aggregate)."New value: +"Sort — a bare column name or SELECT alias only (put expressions in `select` and order by their alias). Defaults to `time_published` (article rows) or `volume` (aggregate rows)."

changedInput schema / properties / q / description

Previous value: -"SQL WHERE on news_article. Optional when search or a scoping param is present."New value: +"WHERE clause over the news_article table. Max 4000 chars. Required UNLESS `search` or a scoping param (`ticker`/`tickers`/`universe`/`from`/`to`) is present — the simplest call needs no SQL. Queryable columns: `time_published`, `title`, `summary`, `source`, `source_domain`, `category`, `authors`, `topics`, `overall_sentiment_score`, `overall_sentiment_label`, `tickers`, `ticker_data`, `banner_image`, `url`, `id`, `created_at` — plus `tk`, the per-ticker UNNEST alias. Signal/state columns are not joinable here."

changedInput schema / properties / search / description

Previous value: -"Full-text search over title+summary (websearch grammar: \"apple earnings\", quoted phrases, OR, -negation). ANDs with q and the scoping params."New value: +"Full-text search over `title` + `summary` — websearch grammar: `apple earnings` (all words), `\"price target\"` (phrase), `chips OR semiconductors`, `-crypto` (negation). Max 200 chars. ANDs with `q` and the scoping params. Language-stemmed English."

changedInput schema / properties / select / description

Previous value: -"Comma-separated columns to include. Defaults to a slim set."New value: +"Columns/expressions to return (max 2000 chars). Defaults to article columns (no `group_by`) or `<group_by cols>, COUNT(*) AS volume` (with `group_by`)."

addedInput schema / properties / ticker

Added value: +{
+  "description": "Articles mentioning this symbol (ANDed with `q`).",
+  "type": "string"
+}

addedInput schema / properties / tickers

Added value: +{
+  "description": "Comma list, up to 50 — articles mentioning ANY of them. Not combinable with `ticker` or `universe`.",
+  "type": "string"
+}

addedInput schema / properties / to

Added value: +{
+  "description": "Articles strictly before this instant — same strict ISO subset, matching `/v2/events`. (`until` accepted as an alias.)",
+  "type": "string"
+}

addedInput schema / properties / universe

Added value: +{
+  "description": "Universe slug — articles mentioning any member. Not combinable with `ticker`/`tickers`.",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "q"
-]
```

Changed1 schema field changedAug 12, 2026

changedInput schema / properties / group_by / description

Previous value: -"Comma-separated columns for aggregation."New value: +"Comma-separated columns for aggregation. Alias a key with `AS` to name its JSON key; un-named expressions are named for you."

Changed2 schema fields changedAug 11, 2026

changedInput schema / properties / q / description

Previous value: -"SQL WHERE on news_article. Required."New value: +"SQL WHERE on news_article. Optional when search or a scoping param is present."

addedInput schema / properties / search

Added value: +{
+  "description": "Full-text search over title+summary (websearch grammar: \"apple earnings\", quoted phrases, OR, -negation). ANDs with q and the scoping params.",
+  "type": "string"
+}

First observedJun 11, 2026

TDQS

A4.1/5.0

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. It discloses that rollups with group_by/having return `truncated: true` instead of paging, and it exposes the SQL-query nature and the `tk` auto-unnest alias. This goes beyond the name and schema, giving the agent a real sense of how the tool behaves, though it does not mention whether the operation is read-only or any performance considerations.

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 five short, information-dense sentences with the core resource and operation front-loaded. Every sentence contributes a distinct fact: SQL querying, row/rollup modes, ticker filtering, full-text search, and truncation behavior. There is no filler or repetition of the detailed schema content.

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 tool's complexity, the input schema is exhaustive with 100% coverage, an output schema exists, and the description covers the non-obvious behaviors an agent must know before calling it. The key modes and the truncation-vs-paging distinction are explained, and the schema handles parameter-level details, so nothing essential is missing.

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 adds some cross-parameter guidance, such as filtering via the `ticker` param or the `tk` alias in `q`, and notes that `search` is full-text over title and summary. However, most of this information is already present in the parameter schemas, so the description adds marginal semantic value beyond them.

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 opens with a specific verb and resource: "SQL query over the news archive." It clearly states the main modes (article rows vs. rollups), full-text search behavior, and ticker filtering, which distinguishes it from sibling tools like tickerbot_list_events or tickerbot_get_series.

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?

The description strongly implies usage by explaining how to filter by ticker, use full-text search, and opt into rollups, but it never explicitly contrasts this tool with alternatives or states when not to use it. An agent can infer the use case but is not directly routed away from similar news/event/listing tools.

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.