NewzAI News MCP server

search_news

Read-only

Searches news for a free-form topic or keyword and returns full details including summary, age, and source URL. To invoke multi-query search, put multiple topics in search_string separated by 'or', for example: 'abc or xyz or pqr'. The region is required. If the user has not provided a country or region, ask them which region they want before calling this tool. Specify the output language and top_k. Note: Language is the output language, not a filter — news in other languages may also be included. Leave search_type as auto (default) unless you have a strong reason to override — the system will intelligently classify it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`top_k`	No	Number of news items to fetch
`region`	Yes	Required region filter for the news search. If missing from the user's request, ask the user which region/country they want.
`language`	No	Language code of the output news content, e.g., 'en' for English. It is not a filter — news in other languages may also be included.	en
`search_type`	No	Defaults to "auto" — the system classifies the best type from the query. You can also specify: - "vector": free-form topic or question benefiting from semantic understanding (e.g., "latest trends in AI", "impact of climate change on agriculture"). - "sparse": specific keywords or phrases (e.g., "Apple earnings report", "Olympics 2024 schedule"). - "exact": precise headline or title match (e.g., "Tesla Model 3 recall", "COVID-19 vaccine approval date"). - "hybrid": mix of free-form and specific keywords (e.g., "effects of inflation on housing market").	auto
`enable_decay`	No	Whether to apply decay for increasing relevance of recent news
`last_n_hours`	No	Time range in hours to fetch recent news, e.g., 24 for news from the last 24 hours
`search_string`	Yes	Free form search string/topic to search for news (e.g., 'latest in AI', '2024 Olympics'). For multi-query search, separate topics with 'or', e.g. 'abc or xyz or pqr'.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 16, 2026

changedInput schema / properties / region / enum

Previous value: -[
-  "india",
-  "united-states",
-  "united-kingdom",
-  "japan"
-]New value: +[
+  "india",
+  "united-states",
+  "united-kingdom",
+  "japan",
+  "international"
+]

Changed5 schema fields changedJun 27, 2026

removedInput schema / properties / search_type / anyOf

Removed value: -[
-  {
-    "enum": [
-      "vector",
-      "hybrid",
-      "sparse",
-      "exact"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

changedInput schema / properties / search_type / default
```
Previous value: -nullNew value: +"auto"
```

changedInput schema / properties / search_type / description

Previous value: -"- Use \"vector\" if the query is a free-form topic or question that would benefit from semantic understanding (e.g., \"latest trends in AI\", \"impact of climate change on agriculture\",\"entertainment\").\n    - Use \"sparse\" if the query consists of specific keywords or phrases without much context (e.g., \"Apple earnings report\", \"Olympics 2024 schedule\").\n    - Use \"exact\" if the query is looking for a precise match, such as a specific news headline or article title (e.g., \"Tesla Model 3 recall\", \"COVID-19 vaccine approval date\").\n    - Use \"hybrid\" if the query contains a mix of free-form language and specific keywords, or if it's ambiguous and could benefit from both semantic and keyword search (e.g., \"effects of inflation on housing market\", \"best smartphones 2024\")."New value: +"Defaults to \"auto\" — the system classifies the best type from the query. You can also specify:\n    - \"vector\": free-form topic or question benefiting from semantic understanding (e.g., \"latest trends in AI\", \"impact of climate change on agriculture\").\n    - \"sparse\": specific keywords or phrases (e.g., \"Apple earnings report\", \"Olympics 2024 schedule\").\n    - \"exact\": precise headline or title match (e.g., \"Tesla Model 3 recall\", \"COVID-19 vaccine approval date\").\n    - \"hybrid\": mix of free-form and specific keywords (e.g., \"effects of inflation on housing market\")."

addedInput schema / properties / search_type / enum

Added value: +[
+  "vector",
+  "hybrid",
+  "sparse",
+  "exact",
+  "auto"
+]

addedInput schema / properties / search_type / type
```
Added value: +"string"
```

Changed9 schema fields changedMay 31, 2026

removedInput schema / properties / region / default
```
Removed value: -"india"
```

changedInput schema / properties / region / description

Previous value: -"Region filter for the news search"New value: +"Required region filter for the news search. If missing from the user's request, ask the user which region/country they want."

changedInput schema / properties / search_string / description

Previous value: -"Free form search string/topic to search for news (e.g., 'latest in AI', '2024 Olympics')"New value: +"Free form search string/topic to search for news (e.g., 'latest in AI', '2024 Olympics'). For multi-query search, separate topics with 'or', e.g. 'abc or xyz or pqr'."

addedInput schema / properties / search_type / anyOf

Added value: +[
+  {
+    "enum": [
+      "vector",
+      "hybrid",
+      "sparse",
+      "exact"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / search_type / default
```
Previous value: -"hybrid"New value: +null
```

changedInput schema / properties / search_type / description

Previous value: -"Use Hybrid search for semantic + similar word search. Select Sparse for keyword-prefered search and Vector for semantic-preferred search. Use Vector search for languages other than English. Use Exact search when an exact match is required but remember it is language and case sensitive."New value: +"- Use \"vector\" if the query is a free-form topic or question that would benefit from semantic understanding (e.g., \"latest trends in AI\", \"impact of climate change on agriculture\",\"entertainment\").\n    - Use \"sparse\" if the query consists of specific keywords or phrases without much context (e.g., \"Apple earnings report\", \"Olympics 2024 schedule\").\n    - Use \"exact\" if the query is looking for a precise match, such as a specific news headline or article title (e.g., \"Tesla Model 3 recall\", \"COVID-19 vaccine approval date\").\n    - Use \"hybrid\" if the query contains a mix of free-form language and specific keywords, or if it's ambiguous and could benefit from both semantic and keyword search (e.g., \"effects of inflation on housing market\", \"best smartphones 2024\")."

removedInput schema / properties / search_type / enum

Removed value: -[
-  "vector",
-  "hybrid",
-  "sparse",
-  "exact"
-]

removedInput schema / properties / search_type / type
```
Removed value: -"string"
```

changedInput schema / required

Previous value: -[
-  "search_string"
-]New value: +[
+  "search_string",
+  "region"
+]

Changed2 schema fields changedMay 20, 2026

addedOutput schema / properties / result / items / properties / news_id
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / result / items / required

Previous value: -[
-  "title",
-  "source",
-  "card_url",
-  "summary",
-  "age",
-  "source_url"
-]New value: +[
+  "news_id",
+  "title",
+  "source",
+  "card_url",
+  "summary",
+  "age",
+  "source_url"
+]

Changed2 schema fields changedMay 17, 2026

changedInput schema / properties / search_type / description

Previous value: -"Use Hybrid search for semantic + similar word search. Select Sparse for similar word-prefered search and Vector for semantic-preferred search. Use Vector search for languages other than English. Use Keyword search when EXACT match is required but remember it is language and case sensitive."New value: +"Use Hybrid search for semantic + similar word search. Select Sparse for keyword-prefered search and Vector for semantic-preferred search. Use Vector search for languages other than English. Use Exact search when an exact match is required but remember it is language and case sensitive."

changedInput schema / properties / search_type / enum

Previous value: -[
-  "vector",
-  "hybrid",
-  "sparse",
-  "keyword"
-]New value: +[
+  "vector",
+  "hybrid",
+  "sparse",
+  "exact"
+]

Changed2 schema fields changedMay 13, 2026

changedInput schema / properties / search_type / description

Previous value: -"Use Hybrid search for semantic + keyword search. Select Sparse for keyword-prefered search and Vector for semantic-preferred search. Use Vector search for languages other than English"New value: +"Use Hybrid search for semantic + similar word search. Select Sparse for similar word-prefered search and Vector for semantic-preferred search. Use Vector search for languages other than English. Use Keyword search when EXACT match is required but remember it is language and case sensitive."

changedInput schema / properties / search_type / enum

Previous value: -[
-  "vector",
-  "hybrid",
-  "sparse"
-]New value: +[
+  "vector",
+  "hybrid",
+  "sparse",
+  "keyword"
+]

AddedApr 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already indicate readOnlyHint=true. Description adds key behaviors: multi-query via 'or', language is not a filter, region requirement, and auto search_type classification. No contradictions.

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?

Five sentences, front-loaded with main purpose. Each sentence adds unique value with no redundancy. Appropriate length for the number of parameters.

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 7 parameters, 2 enums, and output schema exists, description covers key behavioral points (multi-query, region requirement, language note, search_type override advice) and mentions output details. No apparent gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so baseline 3. Description adds meaningful context: multi-query syntax, interaction logic for region, language note, and search_type advice. Enhances understanding beyond bare schema.

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?

Clearly states it searches news for free-form topics or keywords and returns full details (summary, age, source URL). Purpose is distinct from sibling tools like get_news_headlines or get_news_by_category.

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?

Provides actionable guidance: ask for region if missing, specify output language and top_k, leave search_type as auto unless strong reason. However, it does not explicitly differentiate between this and sibling tools (e.g., when to use search_news vs get_news_headlines).

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

All NewzAI News 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.

Resources

Need Help?