Contract
input_schema.json
{
"type": "object",
"required": [
"keyword"
],
"properties": {
"sort": {
"type": "string",
"description": "Sort"
},
"limit": {
"type": "string",
"default": "20",
"description": "Number of articles per page"
},
"offset": {
"type": "string",
"default": "0",
"description": "Offset"
},
"keyword": {
"type": "string",
"description": "Search Keywords"
},
"vertical": {
"type": "string",
"description": "Vertical Type"
},
"search_source": {
"type": "string",
"default": "Normal",
"description": "Search Source"
},
"time_interval": {
"type": "string",
"description": "Time Interval"
},
"vertical_info": {
"type": "string",
"description": "Vertical Info"
},
"search_hash_id": {
"type": "string",
"description": "Search Hash ID"
},
"show_all_topics": {
"type": "integer",
"default": 0,
"description": "Show all topics"
}
},
"additionalProperties": false
}output_schema.json
{
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": [
"string",
"number"
],
"description": "Usually a string, but a bare number on some result types (e.g. the ai_zhida/EBook-material card types)."
},
"type": {
"type": "string",
"description": "The result card's family, e.g. 'search_result' or 'ai_zhida'."
},
"index": {
"type": "number",
"description": "Position of this result on the page."
},
"object": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"url": {
"type": [
"string",
"null"
],
"description": "Whether this result links to a Zhihu page. The link itself is withheld -- value is always `null` regardless of what the upstream data contains."
},
"flag": {
"type": "object",
"properties": {
"flag_text": {
"type": "string",
"description": "e.g. a trending/highlight label."
}
},
"additionalProperties": true
},
"type": {
"type": "string",
"description": "e.g. 'article', 'answer', 'ai_zhida'."
},
"query": {
"type": "string",
"description": "Echo of the search keyword. Only observed on the ai_zhida digest card, where it stands in for the missing title/content fields."
},
"title": {
"type": "string"
},
"content": {
"type": [
"string",
"null"
],
"description": "The body text/HTML of the article or answer, when this is a plain content result. Not present on non-article card types."
},
"excerpt": {
"type": "string"
},
"zfav_count": {
"type": "number",
"description": "An alternate favorites-style count."
},
"description": {
"type": "string"
},
"answer_count": {
"type": "number"
},
"created_time": {
"type": "number",
"description": "Unix seconds."
},
"is_anonymous": {
"type": "boolean"
},
"updated_time": {
"type": "number",
"description": "Unix seconds."
},
"visits_count": {
"type": "number"
},
"voteup_count": {
"type": "number"
},
"comment_count": {
"type": "number"
},
"follower_count": {
"type": "number",
"description": "For question-type results."
},
"favorites_count": {
"type": "number"
},
"follower_count_text": {
"type": "string"
},
"is_zhi_plus_content": {
"type": "boolean",
"description": "True when the content is gated behind Zhihu's paid membership."
}
},
"description": "The underlying content. Shape varies by `object.type` (e.g. 'article', 'answer', 'ai_zhida') -- most of these fields are absent on non-article card types (e.g. an ai_zhida entry carries only `type` and `query`).",
"additionalProperties": true
},
"highlight": {
"type": [
"object",
"null"
],
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
}
},
"description": "The matched keyword highlighted in context with `<em>` tags. Observed `null` on the ai_zhida digest card.",
"additionalProperties": true
},
"query_list": {
"type": "array",
"items": {
"type": "object",
"properties": {
"query": {
"type": "string"
}
},
"additionalProperties": true
},
"description": "Related search terms/suggestions attached to this result."
}
},
"additionalProperties": true
},
"description": "One entry per search hit. Most entries are `type: \"search_result\"` articles/answers (most fields below populated); an `ai_zhida` AI-answer-digest card and other specialized card types can also appear with only `type`, `index`, and `object.query` populated -- e.g. as the first result for a nonsense keyword."
},
"paging": {
"type": "object",
"properties": {
"is_end": {
"type": "boolean",
"description": "True when this is the last page of results."
}
},
"description": "Pagination state for this page of results.",
"additionalProperties": true
},
"domain_info": {
"type": "object",
"properties": {
"first_category": {
"type": "string",
"description": "The topic domain this search matched, e.g. a broad subject label. Present for some queries (e.g. popular keywords) -- may not appear for every input."
}
},
"additionalProperties": true
}
},
"description": "The search result page. A search that matches nothing recognizable still returns this same shape with a short or low-relevance `data` array -- it does not collapse to `{}`.",
"additionalProperties": true
}Pricing
Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.
Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.
| Charge | Rate |
|---|---|
Per call Flat, regardless of what comes back | $0.0020475 |
- Cost basis
- Not recorded
This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.
- Updated
- Oct 12, 2026