Mediastack API
★ Only Publicly Available OpenAPI DocumentData EnrichmentData TransformationapiKey2 EndpointsREST
For Agents
Search live and historical news articles by keyword, country, language, category, and source so an agent can ground its answers in current journalism.
Use for: Search for news about renewable energy in the last 24 hours, Find all articles about a company filed today in English, Retrieve the list of news sources available for the United Kingdom, Get the most recent business headlines from Germany
Not supported: Does not handle web crawling, social media posts, or full article-text licensing — use for structured news article search and source discovery only.
Jentic publishes the only available OpenAPI specification for Mediastack API, keeping it validated and agent-ready. Mediastack is a real-time and historical news data API that aggregates live news articles and headlines from over 7,500 sources across 50+ countries in 13 languages. The API exposes two endpoints: /news for searching articles by keywords, dates, languages, categories, countries, and sources, and /sources for listing available publishers. Use it to enrich agent answers with current news, build news dashboards, or feed content models with topical text.
Install Jentic One Beta
Connect the Mediastack API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Mediastack API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Mediastack API.
Search news articles by free-text keyword across 7,500+ sources
Filter articles by ISO country code, language, and category such as business or technology
Page through historical news using date ranges and offset-limit pagination
List available news sources by language and country to discover what is searchable
Sort results by published date or relevance to surface breaking versus authoritative coverage
Restrict or exclude specific source IDs to control trust and bias in the article feed
Use Cases
Patterns agents use Mediastack API for, with concrete tasks.
★ Brand and Reputation Monitoring
Track every news mention of a brand, executive, or product across 7,500+ international sources without scraping individual outlets. Mediastack returns structured article objects with publication date, source, country, language, and a snippet, which makes it straightforward to dedupe coverage and roll up sentiment downstream. PR teams use this to flag emerging stories within minutes of publication.
Call /news with keywords=Acme Corp, languages=en, sort=published_desc, and date=today and return the article titles, sources, and URLs published in the last six hours.
AI Agent Grounding for Current Events
Give a research agent up-to-the-minute news context so its answers are not stuck at the model's training cutoff. The /news endpoint returns recent articles filtered by topic, language, and country, which the agent can summarise inline. This pattern lifts factuality on questions about ongoing events without exposing the agent to arbitrary web scraping.
Search Mediastack for keywords=climate summit and languages=en limited to the last 48 hours, then summarise the three most-cited stories with their source URLs.
Topical Content Curation
Feed a newsletter or internal briefing with curated articles by topic, country, and language without manually scanning each outlet. Mediastack's category filter (general, business, entertainment, health, science, sports, technology) and country filter let an agent assemble a tightly scoped reading list per audience segment. This compresses hours of editorial scanning into a single API call per audience.
Fetch business-category news for countries=us,gb in English published today, dedupe by URL, and return the top 10 by source authority for inclusion in the morning briefing.
Multilingual Market Intelligence
Search for industry signals in 13 languages so a market-intelligence agent does not miss non-English-language coverage of competitors and regulators. The /sources endpoint helps the agent confirm coverage in each market before searching, and /news returns articles tagged with language and country for downstream filtering. This is especially useful for regulated industries where regional press breaks news first.
Use /sources to list news sources for country=de language=de, then call /news with keywords=Bundeskartellamt and languages=de for the last seven days and return the unique sources covering it.
Key Endpoints
2 endpoints — jentic publishes the only available openapi specification for mediastack api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/news
Search live and historical news articles
GET
/sources
List available news sources
GET
/news
Search live and historical news articles
GET
/sources
List available news sources
Why Jentic?
Three things that make agents converge on Jentic-routed access.
Credential isolation
Your Mediastack access_key is stored encrypted in the Jentic vault and injected as the query parameter at execution time. Agents never see the raw key.
Intent-based discovery
Agents search by intent (e.g. 'find recent news about a topic') and Jentic returns the matching Mediastack /news operation with its parameter schema.
Time to first call
Direct Mediastack integration: a few hours wiring the auth and pagination plus retry logic. Through Jentic: under 15 minutes — search, load schema, execute.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Mediastack API through Jentic.
Why is there no official OpenAPI spec for Mediastack API?
Mediastack does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Mediastack API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Mediastack API use?
Mediastack uses an API key passed as the access_key query parameter. Through Jentic the key is stored encrypted in the vault and injected at execution time, so the agent never sees the raw value.
Can I retrieve historical news articles with the Mediastack API?
Yes. The /news endpoint accepts a date filter that supports both single dates and ranges, allowing you to page back through historical coverage subject to the retention window of your Mediastack plan.
What are the rate limits for the Mediastack API?
Rate limits are tied to plan: the free tier allows up to 500 requests per month and the paid tiers raise that ceiling progressively. Plan also gates HTTPS access and historical depth, so check your dashboard before scaling agent calls.
How do I search news for a topic through Jentic?
Search Jentic for search news articles, load the schema for the /news operation, and execute with keywords, languages, and date parameters. Jentic returns the article list with title, source, URL, and published_at fields ready for the agent to summarise.
Which languages and countries does Mediastack cover?
Mediastack covers 13 languages including English, German, Spanish, French, Italian, and Portuguese, sourced from publishers across more than 50 countries. Use /sources with the languages and countries filters to enumerate exactly which publishers are available before searching.
GET STARTED