canonical: https://jentic.com/apis/eventregistry.org/eventregistry # Event Registry REST API The Event Registry REST API runs text analytics over news content and retrieves the articles and events behind it. Your agent annotates text to identify people, locations, and organizations, classifies sentiment, categorizes documents, detects language, and measures semantic similarity between documents. It also searches news articles and the real-world events that group them, and resolves concept, category, source, and location names into the URIs those searches expect. ## For AI agents Run NLP over news text: annotate entities, score sentiment, categorize and detect language, measure semantic similarity, and search news articles and events. ## Scope Does not publish content, send alerts, or store your own documents. Use for retrieving news articles and events and running text analytics only. ## Capabilities - Annotate text to identify people, locations, organizations, and topics - Score sentiment and categorize documents into predefined categories - Detect the language of a document and measure semantic similarity between two - Search news articles by concept, source, and date - Retrieve news events and the articles that report them - Resolve concept, category, source, and location names into query URIs ## Use cases ### Agent-Driven Text Intelligence An AI agent connected through Jentic enriches raw text by annotating its entities, scoring its sentiment, and categorizing it, then detects its language when the source is unknown. Because each analysis is its own operation, the agent assembles exactly the pipeline a task needs, such as entity extraction followed by sentiment, without pulling an all-in-one model. Example prompt: Annotate an article to extract its organizations, then score the article's sentiment ### News Monitoring A monitoring workflow tracks coverage of a topic by searching news articles and the events that group them. The Event Registry API queries articles by concept, source, and date and returns the matching events, so an agent builds a running feed of relevant coverage from across many sources. Example prompt: Search articles for a concept over the last week and group the matches by the events they belong to ### Query Building with URIs Before a precise search, an agent resolves human names into the identifiers Event Registry expects. The autosuggest operations map a concept, category, source, or location label to its URI, letting an agent turn 'articles about renewable energy from Reuters' into a URI-based query that returns clean results. Example prompt: Resolve a concept label and a source name to their URIs and build an article search from them ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/api/v1/article/getArticles` | Search news articles by conditions | | GET | `/api/v1/event/getEvents` | Retrieve news events by conditions | | GET | `/annotate` | Identify entities mentioned in text | | GET | `/categorize` | Categorize text into predefined categories | | GET | `/sentiment` | Vocabulary-based sentiment detection | | GET | `/detectLanguage` | Detect the language of input text | | GET | `/semanticSimilarity` | Compute semantic similarity of two documents | | GET | `/api/v1/getEventForText` | Identify the event that best matches input text | ## Key resources - **Text analytics** — Annotate, categorize, score sentiment, and detect language - **Semantic similarity** — Compute similarity between two documents - **Articles** — Search and retrieve news articles - **Events** — Retrieve news events and the articles reporting them - **Autosuggest** — Resolve concept, category, source, and location names into URIs ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 35 / 100 - **Maturity:** Non-Ready - **Dimensions:** - Foundational Compliance: 57 / 100 - Developer Experience & Jentic Compatibility: 33 / 100 - AI-Readiness & Agent Experience: 27 / 100 - Agent Usability: 94 / 100 - Security: 15 / 100 - AI Discoverability: 90 / 100 - **View full report:** https://jentic.com/apis/eventregistry.org/eventregistry/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring Event Registry by hand means managing the `apiKey` query parameter and learning which operations are analytics versus news search across its surface. Through Jentic you install once, import the Event Registry REST API from the API Directory, store the key once, and your agent calls the operations it needs. - **Permission scoping:** Every Event Registry operation is a read that queries by parameters, so a rule can allow only the ones your agent needs, such as article search and sentiment analysis. There are no write or delete operations to expose, and the agent is held to the analyses you intend. - **Credential handling:** Your Event Registry API key is held by your own Jentic One instance, encrypted, and injected into the query string at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'extract entities from text' or 'search recent news', and Jentic returns the matching Event Registry operation with its input schema so the agent calls the right analysis or search endpoint. ## Related APIs - **NewsAPI** — A straightforward news-article search API, an alternative when you need headlines without the NLP layer. - **GNews API** — A news search API over global sources, an alternative for lighter-weight article retrieval. - **NLP Cloud API** — General-purpose NLP models that complement Event Registry for tasks beyond its news-focused analytics. ## FAQ ### What authentication does the Event Registry REST API use? The Event Registry REST API authenticates with an API key passed as the `apiKey` query parameter, per its OpenAPI spec. Through Jentic the key is held by your own Jentic One instance and attached to each request at execution time, so it never appears in your agent's prompt or logs. ### Can I extract entities and sentiment from text with the Event Registry API? Yes. The API annotates text to identify people, locations, and organizations, scores sentiment, categorizes documents, and detects language. Your agent can chain these analyses, for example annotating an article and then scoring its sentiment, as separate calls. ### What are the rate limits for the Event Registry REST API? The OpenAPI spec does not specify rate limits, and Event Registry meters usage by token allowance per plan. Check the Event Registry documentation at https://eventregistry.org for the current token limits before running high-volume analysis. ### Is there an Event Registry MCP server? You do not need an MCP server to give your agent the Event Registry REST API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent discovers the analytics and news-search operations it needs on demand without loading an extra server's tool definitions into its context. ### Can I limit what my agent is allowed to do with the Event Registry REST API? Yes. Every operation here is a read, so write a rule that allows only the ones your agent needs, such as article search and sentiment analysis, and leave the rest unavailable. The agent can analyze and search but cannot change anything, and every call it makes is logged. ### How do I analyze news text through Jentic? Install the Jentic One command line with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add the Event Registry REST API from the Jentic directory and search by intent such as 'extract entities from an article'. Jentic returns the matching operation with its input schema so your agent builds a valid request. To run it on your own infrastructure, install Jentic One from its GitHub repo.