Gate News MCP

news_feed_search_x

Read-onlyIdempotent

[Read] Search and analyze X/Twitter discussions for a topic, with tweet-level evidence and cited posts. Aggregate social mood, sentiment score, or positive/negative split -> get_social_sentiment. Open-web pages -> web_search. Multi-platform social search -> search_ugc. Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.

Input Schema

TableJSON Schema

Name	Required	Description
`days`	No	Lookback days when time_range omitted; omitted or <=0 treated as 1 (24h); min 1 when explicitly set.
`lang`	No	Answer language: zh (default) / en / auto.
`model`	No	Override configured Grok model id.
`query`	No	X/Twitter topic for tweet-level evidence and cited posts; English recommended. Empty returns no results. Aggregate social mood, sentiment score, or positive/negative split -> get_social_sentiment. Open-web pages -> web_search. Multi-platform social search -> search_ugc.
`time_range`	No	Preferred recency window for search_x: 1h / 24h (default) / 7d. Takes precedence over days when set.
`allowed_handles`	No	Include these X handles without @, max 10; mutually exclusive with excluded_handles.
`excluded_handles`	No	Exclude these handles, max 10.
`enable_image_understanding`	No	Analyze images in posts.
`enable_video_understanding`	No	Analyze video in posts.

Output Schema

TableJSON Schema

Name	Required	Description
`days`	No
`lang`	No
`count`	Yes
`items`	Yes
`model`	No
`query`	No
`total`	Yes
`source`	No
`content`	Yes	Same as summary for legacy clients; tweet-level X/Twitter evidence—not headline index (search_news).
`summary`	Yes	xAI: synthesized narrative from X/Twitter discussions with tweet-level evidence (same as content; always present). Not open-web synthesis with cited external pages (web_search). Not per-coin sentiment KPIs over a time range (get_social_sentiment).
`to_date`	No
`from_date`	No
`disclaimer`	No	Fixed disclaimer on successful xAI response.
`key_points`	Yes	xAI: bullet points from cited posts; empty array if none. Not briefing-style platform news lists (search_news).
`duration_ms`	Yes
`cited_tweets`	Yes	xAI: tweet-level evidence and cited posts; fields depend on model and citations.
`allowed_handles`	No
`sentiment_label`	Yes	xAI: bullish / bearish / neutral for the discussion; empty if unknown. Not per-coin sentiment label KPIs (get_social_sentiment).
`sentiment_score`	No	xAI: 0-100 tone for this X/Twitter topic; JSON null if unknown; pairs with sentiment_label. Not per-coin aggregate positive/negative split (get_social_sentiment).
`excluded_handles`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed14 schema fields changedAug 27, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / allowed_handles / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

changedInput schema / properties / excluded_handles / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

addedOutput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / properties / allowed_handles / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

addedOutput schema / properties / cited_tweets / items / additionalProperties
```
Added value: +false
```

changedOutput schema / properties / cited_tweets / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

changedOutput schema / properties / excluded_handles / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

addedOutput schema / properties / items / items / additionalProperties
```
Added value: +true
```

changedOutput schema / properties / items / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

changedOutput schema / properties / key_points / type

Previous value: -"array"New value: +[
+  "null",
+  "array"
+]

addedOutput schema / properties / sentiment_score / description

Added value: +"xAI: 0-100 tone for this X/Twitter topic; JSON null if unknown; pairs with sentiment_label. Not per-coin aggregate positive/negative split (get_social_sentiment)."

removedOutput schema / properties / sentiment_score / oneOf

Removed value: -[
-  {
-    "description": "xAI: 0-100 tone for this X/Twitter topic; JSON null if unknown; pairs with sentiment_label. Not per-coin aggregate positive/negative split (get_social_sentiment).",
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / sentiment_score / type
```
Added value: +[
+  "null",
+  "integer"
+]
```

Changed22 schema fields changedAug 21, 2026

changedInput schema / properties / allowed_handles / description

Previous value: -"xAI only: include these X handles without @, max 10; mutually exclusive with excluded_handles."New value: +"Include these X handles without @, max 10; mutually exclusive with excluded_handles."

removedInput schema / properties / coin

Removed value: -{
-  "description": "Platform fallback: maps to tickers for feed-style items when xAI path is unused—tweet-level X evidence remains the primary tool goal; per-coin sentiment KPIs -> get_social_sentiment.",
-  "type": "string"
-}

changedInput schema / properties / days / description

Previous value: -"xAI only: lookback days when time_range omitted; omitted or <=0 treated as 1 (24h); min 1 when explicitly set."New value: +"Lookback days when time_range omitted; omitted or <=0 treated as 1 (24h); min 1 when explicitly set."

changedInput schema / properties / enable_image_understanding / description

Previous value: -"xAI only: analyze images in posts."New value: +"Analyze images in posts."

changedInput schema / properties / enable_video_understanding / description

Previous value: -"xAI only: analyze video in posts."New value: +"Analyze video in posts."

removedInput schema / properties / end_time

Removed value: -{
-  "description": "Platform fallback: maps to to.",
-  "type": "string"
-}

changedInput schema / properties / excluded_handles / description

Previous value: -"xAI only: exclude these handles, max 10."New value: +"Exclude these handles, max 10."

changedInput schema / properties / lang / description

Previous value: -"Answer language: zh (default) / en / auto. Also used by platform fallback as MCP local lang filter."New value: +"Answer language: zh (default) / en / auto."

removedInput schema / properties / limit

Removed value: -{
-  "description": "Platform fallback: page_size, default 10.",
-  "type": "integer"
-}

changedInput schema / properties / model / description

Previous value: -"xAI only: override configured Grok model id."New value: +"Override configured Grok model id."

removedInput schema / properties / page

Removed value: -{
-  "description": "Platform fallback: page number.",
-  "type": "integer"
-}

removedInput schema / properties / platform

Removed value: -{
-  "description": "Platform fallback: platform.",
-  "type": "string"
-}

removedInput schema / properties / platform_type

Removed value: -{
-  "description": "Platform fallback: maps when platform omitted.",
-  "type": "string"
-}

changedInput schema / properties / query / description

Previous value: -"X/Twitter topic for tweet-level evidence and cited posts; English recommended. xAI: empty returns no results. Aggregate social mood, sentiment score, or positive/negative split -> get_social_sentiment. Open-web pages -> web_search. Multi-platform social search -> search_ugc. Platform fallback matches search_news.query semantics."New value: +"X/Twitter topic for tweet-level evidence and cited posts; English recommended. Empty returns no results. Aggregate social mood, sentiment score, or positive/negative split -> get_social_sentiment. Open-web pages -> web_search. Multi-platform social search -> search_ugc."

removedInput schema / properties / similarity_score

Removed value: -{
-  "description": "Platform fallback: similarity threshold.",
-  "type": "string"
-}

removedInput schema / properties / sort_by

Removed value: -{
-  "description": "Platform fallback: sort field.",
-  "type": "string"
-}

removedInput schema / properties / start_time

Removed value: -{
-  "description": "Platform fallback: maps to from (Unix sec).",
-  "type": "string"
-}

removedInput schema / properties / top_total_score

Removed value: -{
-  "description": "Platform fallback: heat vs similarity.",
-  "type": "integer"
-}

removedOutput schema / properties / coin

Removed value: -{
-  "type": "string"
-}

changedOutput schema / properties / disclaimer / description

Previous value: -"Fixed disclaimer on xAI success; empty on platform fallback."New value: +"Fixed disclaimer on successful xAI response."

removedOutput schema / properties / platform
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / properties / platform_type
```
Removed value: -{
-  "type": "string"
-}
```

Changed1 schema field changedMay 22, 2026

changedInput schema / properties / days / description

Previous value: -"xAI only: lookback days; default 7, min 1."New value: +"xAI only: lookback days when time_range omitted; omitted or <=0 treated as 1 (24h); min 1 when explicitly set."

Changed5 schema fields changedMay 20, 2026

changedOutput schema / properties / items / items

Previous value: -trueNew value: +{
+  "type": "object"
+}

removedOutput schema / properties / sentiment_score / description

Removed value: -"xAI: 0-100 tone for this X/Twitter topic; JSON null if unknown; pairs with sentiment_label. Not per-coin aggregate positive/negative split (get_social_sentiment)."

addedOutput schema / properties / sentiment_score / oneOf

Added value: +[
+  {
+    "description": "xAI: 0-100 tone for this X/Twitter topic; JSON null if unknown; pairs with sentiment_label. Not per-coin aggregate positive/negative split (get_social_sentiment).",
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / sentiment_score / type
```
Removed value: -"integer"
```

changedOutput schema / required

Previous value: -[
-  "summary",
-  "content",
-  "sentiment_score",
-  "sentiment_label",
-  "key_points",
-  "cited_tweets",
-  "total",
-  "count",
-  "items",
-  "duration_ms"
-]New value: +[
+  "summary",
+  "content",
+  "sentiment_label",
+  "key_points",
+  "cited_tweets",
+  "total",
+  "count",
+  "items",
+  "duration_ms"
+]

First observedApr 16, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds critical behavioral context beyond these: it clarifies the tool accesses public research data only, does not involve account access or trading, and explicitly disclaims investment advice. This goes beyond the annotations and sets clear expectations for the agent.

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 (about 4 sentences), front-loads the core purpose, and then efficiently lists alternatives and safety constraints. Every sentence earns its place without redundancy or fluff, making it easy for an agent to parse quickly.

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?

For a tool with 9 optional parameters, an output schema, and rich annotations, the description is complete. It clearly states what the tool does, its scope, its exclusions, and how it differs from siblings. The output schema covers return values, and the annotations cover safety/read-only aspects, so nothing essential is missing for correct invocation.

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%, so the schema already documents all 9 parameters thoroughly. The description adds minimal parameter-level meaning—it mentions the query is 'for a topic' and aggregates sentiment, but these are largely redundant with the schema's own parameter descriptions. Baseline 3 is appropriate when the schema carries the burden.

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 states a specific verb ('Search and analyze') with a clear resource (X/Twitter discussions) and scope ('for a topic, with tweet-level evidence and cited posts'). It distinguishes itself from siblings by explicitly naming get_social_sentiment, web_search, and search_ugc as alternatives for different needs, leaving no ambiguity about what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

The description provides explicit when-to-use vs. when-not-to-use guidance: it directs aggregate sentiment tasks to get_social_sentiment, open-web pages to web_search, and multi-platform search to search_ugc. It also states the tool's limitations ('Read-only public research data. No account access, no order placement or fund transfers'), giving the agent clear decision criteria.

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

All Gate News MCP 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.