Search1API MCP Server

News search

news

Read-only

Search current articles on recent events, announcements, or coverage and return citable results with titles, URLs, snippets, and optional extracted text.

Instructions

Search current news when the user asks about recent events, announcements, or coverage. Returns citable article results with title, URL, snippet, and optional extracted text.

Input Schema

Name	Required	Description	Default
`query`	Yes	Short, focused news query
`time_range`	No	Only return articles published within this window; use day for breaking news
`max_results`	No	How many articles the answer needs; a handful suits most questions, more suits broad coverage
`crawl_results`	No	Number of top articles to retrieve as full pages. Each successful retrieval adds 1 credit to the base 1-credit news request
`exclude_sites`	No	News domains to exclude
`include_sites`	No	News domains to include
`search_service`	No	News engine to use; hackernews returns Hacker News discussions instead of publisher articles	bing

Output Schema

Name	Required	Description	Default
`results`	Yes	Matching sources, most relevant first; read any url in full with crawl

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.9.0Oct 29, 2026

changedInput schema / properties / max_results / description

Previous value: -"Maximum number of articles to return"New value: +"How many articles the answer needs; a handful suits most questions, more suits broad coverage"

changedInput schema / properties / search_service / description

Previous value: -"News search engine to use"New value: +"News engine to use; hackernews returns Hacker News discussions instead of publisher articles"

changedInput schema / properties / time_range / description

Previous value: -"Optional recency window; use day for breaking news"New value: +"Only return articles published within this window; use day for breaking news"

addedOutput schema / properties / results / description

Added value: +"Matching sources, most relevant first; read any url in full with crawl"

Changed1 schema field changedv0.8.0Oct 14, 2026

changedInput schema / properties / time_range / enum

Previous value: -[
-  "day",
-  "month",
-  "year"
-]New value: +[
+  "day",
+  "week",
+  "month",
+  "year"
+]

Changed11 schema fields changedv0.4.0Jul 29, 2026

changedInput schema / properties / crawl_results / description

Previous value: -"Number of top results to crawl for full webpage content. Each successfully crawled page adds 1 credit to the base 1-credit news request"New value: +"Number of top articles to retrieve as full pages. Each successful retrieval adds 1 credit to the base 1-credit news request"

addedInput schema / properties / crawl_results / minimum
```
Added value: +0
```

changedInput schema / properties / exclude_sites / description

Previous value: -"List of sites to exclude from search. Only use when you need to explicitly filter out specific domains from results"New value: +"News domains to exclude"

changedInput schema / properties / include_sites / description

Previous value: -"List of sites to include in search. Only use when you need special results from sites not available in search_service"New value: +"News domains to include"

changedInput schema / properties / max_results / description

Previous value: -"Maximum number of results to return"New value: +"Maximum number of articles to return"

addedInput schema / properties / max_results / maximum
```
Added value: +50
```
addedInput schema / properties / max_results / minimum
```
Added value: +1
```

changedInput schema / properties / query / description

Previous value: -"Search query, be simple and concise"New value: +"Short, focused news query"

changedInput schema / properties / search_service / description

Previous value: -"Specify the news engine to use. Choose based on your specific needs"New value: +"News search engine to use"

changedInput schema / properties / time_range / description

Previous value: -"Time range for search results, only use when specific time constraints are required"New value: +"Optional recency window; use day for breaking news"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Stable identifier for this result; for web results this is the canonical URL",
+            "type": "string"
+          },
+          "metadata": {
+            "additionalProperties": true,
+            "description": "Additional source metadata",
+            "type": "object"
+          },
+          "text": {
+            "description": "Result snippet or extracted page text when available",
+            "type": "string"
+          },
+          "title": {
+            "description": "Human-readable result title",
+            "type": "string"
+          },
+          "url": {
+            "description": "Canonical URL that clients can cite and users can open",
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "title",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "results"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.3.1Jul 28, 2026

changedInput schema / properties / crawl_results / description

Previous value: -"Number of results to crawl for full webpage content, useful when search result summaries are insufficient for complex queries"New value: +"Number of top results to crawl for full webpage content. Each successfully crawled page adds 1 credit to the base 1-credit news request"

First observedv0.1.8May 8, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnly, openWorld, non-idempotent, non-destructive, so the safety profile is covered. The description adds that results are citable and may include extracted full text, but it omits the credit cost implied by crawl_results and any note that results are external/unverified content. Useful addition, not rich behavioral context.

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?

Two sentences, zero waste: the first covers when to use it, the second covers what comes back. Front-loaded with the trigger condition.

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?

With an output schema present and full schema coverage, the description needs only to establish purpose, trigger, and general shape of results, all of which it does. The only meaningful gap is that cost-bearing behavior (crawl_results consuming extra credits) is left entirely to the schema.

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% and every parameter — including time_range, max_results, and the include/exclude site lists — is documented in the schema, so the baseline of 3 applies. The description adds no parameter-level guidance beyond what the schema already states.

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?

Names a specific verb and resource ("Search current news") and scopes it to recent events, announcements, and coverage, which distinguishes it from the generic 'search' and 'crawl' siblings in spirit. It does not explicitly name a sibling or state the boundary, 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 Guidelines4/5

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

The opening clause gives a clear trigger condition (user asks about recent events, announcements, or coverage), which is exactly the context an agent needs. It offers no exclusions or named alternatives (e.g., when to prefer 'search' or 'trending' instead), so it is clear context without routing.

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

Deploy Server