# Get news and sentiment for a ticker

> Get news and sentiment for a ticker: 5 companies fully do it, 4 with a limit, 15 carry the tag. Every listing in Financial market data with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/market-data.market-news/
- Markdown: https://www.anchorterminal.com/niches/market-data.market-news/index.md (~1,200 tokens)
- Slim: https://www.anchorterminal.com/niches/market-data.market-news/index.min.md (~280 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/market-data.market-news/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

Four or more companies' docs show a full fit.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 5 | 4 | 15 | 9 | 4 |

## What counts as done

A bounded list of articles with time, source, ticker tags and URL, honouring the limit asked, with publisher and feed attribution kept.

Measured, for our own tests: 10 items under 4,000 tokens.

How agents ask for it: any news on Nvidia today; what's moving this stock; sentiment on my holdings this week

## Does the job

The docs show it meets the test above, and nothing we read says otherwise.

- **Benzinga (Benzinga)**: GET news takes tickers, dateFrom, updatedSince and pageSize (default 15, max 100), with displayOutput headline, abstract or full, so ten headline items fit a small budget; Benzinga is the publisher.
- **Financial Datasets (Financial Datasets, Inc.)**: GET /news by ticker returns title, source, date and url with limit default 5, max 10, and cursor paging, so ten items is one bounded call.
- **Intrinio (Intrinio, Inc.)**: GET /companies/{id}/news takes page_size, source and sentiment filters and returns title, publication_date, url and summary per article, with the source named.
- **Massive (formerly Polygon.io) (Massive.com, Inc.)**: GET news takes ticker, published_utc ranges and limit (default 10, max 1,000) and returns publisher, published_utc, article_url and summary.
- **Tiingo (Tiingo Inc.)**: GET /tiingo/news takes tickers, source, startDate, endDate, limit (default 100, max 1,000) and offset, and returns title, url, description, publishedDate, source and tags.

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Alpha Vantage (Alpha Vantage Inc.)**: NEWS_SENTIMENT filters by tickers, topics and time_from with limit (default 50, up to 1,000); acc-20's ignored limit on the MCP server was closed in October 2025, but acc-17 saw a news request pass 321k tokens.
- **EODHD (Unicorn Data Services)**: GET /news?s=&limit= returns date, title, full content, link, symbols and tags at 5 calls; full article content makes ten items heavy, and the publisher is only implied by the link.
- **Finnhub (Finnhub)**: /company-news takes symbol, from and to and returns datetime, headline, source, summary and url, but has no limit parameter, so the item count depends on the date window; North American companies only.
- **Twelve Data (Twelve Data Pte. Ltd.)**: The only news-like endpoint in the reference is /press_releases (title, datetime, body, outputsize paging), official company releases rather than third-party news with source and URL.

## Couldn't check

The docs were closed to us, or silent. These carry no mark either way.

- **Financial Modeling Prep (Financial Modeling Prep)**: site.financialmodelingprep.com answered 403 to robots.txt, so no FMP docs were opened; acc-35 moves news to cached FMP but says nothing of limits or attribution.

- not this job: Databento (Databento, Inc.): No news feed.
- not this job: Eulerpool Financial Data API (Eulerpool Research Systems Pte. Ltd.): News is a single RSS feed of all news with language and type only; no ticker filter, time window or limit.

2 listings in the category were added after this reading and aren't marked yet.

## What stops agents finishing

- limit parameter ignored
- news request larger than the model's context
- attribution owed in display

## Around it

Before: chat.user-question. After: reasoning.summarise, notifications.send-alert.

## Where this comes from

Weight 9 of 100 in Financial market data: 4 of 46 accounts (4 of 48 mentions); Alpha Vantage news size and limit problems, Tiingo attribution

As data: https://www.anchorterminal.com/api/v1/use-cases/market-data.market-news.json, or the MCP tool get_use_case with id market-data.market-news. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
