NewzAI News MCP server

set_user_preferences

Adds one or more news preferences for the authenticated user. Each preference is defined by news category(or search parameter), region, output language. Optional values include last_n_hours for recency filter, search_type, and enable_decay. Leave search_type as auto (default) — the system will classify the best type from the category. Existing preferences are not removed — new ones are appended. Login is required to access this tool.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`preferences`	Yes	List of preferences to add for the user

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 16, 2026

addedInput schema / properties / preferences / items / properties / region / enum

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

addedOutput schema / properties / result / items / properties / region / enum

Added value: +[
+  "india",
+  "united-states",
+  "united-kingdom",
+  "japan",
+  "australia",
+  "canada",
+  "germany",
+  "international"
+]

Changed4 schema fields changedJun 27, 2026

changedInput schema / properties / preferences / items / properties / search_type / default
```
Previous value: -"hybrid"New value: +"auto"
```

changedInput schema / properties / preferences / items / properties / search_type / description

Previous value: -"Search algorithm to use for this preference. Optional. Default is HYBRID. Use HYBRID for a mix of semantic and keyword search, SPARSE for keyword-preferred search, VECTOR for semantic-preferred search, and EXACT when an exact match is required (case and language sensitive)."New value: +"Search algorithm to use for this preference. Defaults to auto — the system classifies the best type from the category. You can also specify: hybrid for semantic + keyword mix, sparse for keyword-preferred, vector for semantic-preferred, exact for precise title match."

changedInput schema / properties / preferences / items / properties / search_type / enum

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

changedOutput schema / properties / result / items / properties / search_type / enum

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

Changed11 schema fields changedMay 17, 2026

removedInput schema / properties / preferences / items / properties / daily_refresh_time

Removed value: -{
-  "default": "10:00",
-  "description": "Daily refresh time in HH:MM 24-hour format (e.g., '08:00', '22:30')",
-  "type": "string"
-}

addedInput schema / properties / preferences / items / properties / enable_decay

Added value: +{
+  "default": true,
+  "description": "Whether to apply decay for increasing relevance of recent news for this preference. Optional. Default is True.",
+  "type": "boolean"
+}

addedInput schema / properties / preferences / items / properties / last_n_hours

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Time range in hours to fetch recent news for this preference, e.g., 24 for news from the last 24 hours. Optional."
+}

addedInput schema / properties / preferences / items / properties / search_type

Added value: +{
+  "default": "hybrid",
+  "description": "Search algorithm to use for this preference. Optional. Default is HYBRID. Use HYBRID for a mix of semantic and keyword search, SPARSE for keyword-preferred search, VECTOR for semantic-preferred search, and EXACT when an exact match is required (case and language sensitive).",
+  "enum": [
+    "vector",
+    "hybrid",
+    "sparse",
+    "exact"
+  ],
+  "type": "string"
+}

addedInput schema / properties / preferences / items / properties / similarity_threshold

Added value: +{
+  "default": "none",
+  "description": "Similarity level for news articles for this preference. Optional. Can be 'high', 'medium', or 'none'. If not specified, defaults to 'none'.",
+  "enum": [
+    "high",
+    "medium",
+    "none"
+  ],
+  "type": "string"
+}

removedOutput schema / properties / result / items / properties / daily_refresh_time
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / result / items / properties / enable_decay
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / result / items / properties / last_n_hours

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / result / items / properties / search_type

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

addedOutput schema / properties / result / items / properties / similarity_threshold

Added value: +{
+  "enum": [
+    "high",
+    "medium",
+    "none"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / result / items / required

Previous value: -[
-  "id",
-  "category",
-  "region",
-  "language",
-  "daily_refresh_time"
-]New value: +[
+  "id",
+  "category",
+  "region",
+  "language",
+  "last_n_hours",
+  "search_type",
+  "enable_decay",
+  "similarity_threshold"
+]

AddedApr 17, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description discloses additive behavior (appending, not removing) and login requirement, which goes beyond what annotations provide (readOnlyHint=false, destructiveHint=false). There is no contradiction with annotations.

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?

The description is concise (three sentences) and well-structured: purpose first, then details on behavior and recommendations. Every sentence adds necessary context without redundancy.

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 the tool's complexity (with an array of nested preferences) and the presence of an output schema, the description adequately covers purpose, prerequisites, behavior, and parameter guidance. It is complete for an AI agent to use correctly.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds valuable guidance beyond the schema, such as recommending auto for search_type and clarifying that existing preferences are not removed. This improves the agent's understanding of parameter usage.

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?

The description clearly states the verb 'adds' and the resource 'news preferences for the authenticated user', distinguishing it from siblings like get_user_preferences (read) and update_user_preferences (modify). It is specific and unambiguous.

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 description provides context such as login requirement and that existing preferences are appended, not removed. It also recommends leaving search_type as auto. However, it does not explicitly compare with sibling tools like get_user_preferences or update_user_preferences to guide selection.

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?