Total CMS
Read-only Total CMS docs: Twig signatures, field types, schema options, the CLI and the REST API.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'fetch' suggests web access but openWorldHint=false在 fetch 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"docs": {
"url": "https://totalcms.co/mcp"
}
}
}遠端端點
https://totalcms.co/mcpstreamable-http它能做什麼
工具清單
工具（20）
🟢describe_collection(collection)
Describe one collection in detail. Returns the collection metadata plus a properties array — each entry is a property with its type, description, and indexed/filterable/sortable flags. Call list_collections first to find a collection id, then describe_collection to see what is queryable inside it. `indexed: true` means the property appears in query_collection / search_collection results (and may be filterable/sortable). `indexed: false` means the property exists on objects but is not returned by query/search — retrieve it through get_object instead.
輸入結構描述
{
"type": "object",
"properties": {
"collection": {
"type": "string",
"description": "Collection id (slug-form). Use list_collections to discover available collections.",
"examples": [
"blog",
"products",
"team"
]
}
},
"required": [
"collection"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
],
"description": "Collection-level mcp.description, falling back to the schema description."
},
"url_pattern": {
"type": "string",
"description": "URL template for objects, e.g. \"/blog/{id}\". Empty string when no pattern is configured."
},
"access": {
"type": "string",
"enum": [
"admin",
"apikey",
"authenticated",
"public"
],
"description": "Persona that can query this collection."
},
"total_objects": {
"type": "integer"
},
"ownership": {
"type": [
"string",
"null"
],
"description": "Set when the collection limits the caller to their own objects, or has fields only the site sets: what the caller sees and may change."
},
"properties": {
"type": "array",
"description": "One entry per exposed property (mcp.expose:false fields are stripped). Per-property mcp.description is surfaced here when set.",
"items": {
"type": "object",
"required": [
"name",
"type",
"indexed",
"filterable",
"sortable"
],
"additionalProperties": false,
"properties": {
"name": {
"type": "string"
},
"type": {
"type": "string",
"description": "Schema field type (text, number, date, toggle, etc.)."
},
"description": {
"type": [
"string",
"null"
],
"description": "Resolved property description — mcp.description → help → label."
},
"indexed": {
"type": "boolean",
"description": "True when the property appears in query/search results. False = available via get_object only."
},
"filterable": {
"type": "boolean"
},
"sortable": {
"type": "boolean"
}
}
}
}
},
"required": [
"id",
"access",
"total_objects",
"properties"
],
"additionalProperties": false
}🟢describe_view(id)
Describe one data view in detail. Returns metadata (id, name, description, last_built, access, total_items) plus output_shape — the list of keys present on the first cached item, sampled so agents can compose effective query_view / get_view calls. Admin callers also receive the view's Twig definition for dev visibility. Use list_views to discover view ids first.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "View id. Use list_views to discover available views.",
"examples": [
"recent-posts",
"monthly-sales-summary"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"last_built": {
"type": "string"
},
"access": {
"type": "string",
"enum": [
"admin",
"apikey",
"authenticated",
"public"
]
},
"total_items": {
"type": "integer"
},
"output_shape": {
"type": "array",
"description": "Keys present on the first cached item. Empty when the view has never been built or produced no items.",
"items": {
"type": "string"
}
},
"definition": {
"type": "string",
"description": "Twig source for the view. Admin persona only — absent for public callers."
}
},
"required": [
"id",
"name",
"access",
"total_items",
"output_shape"
],
"additionalProperties": true
}🟢docs_get(path)
Fetch a full Total CMS documentation page as markdown by its path (as returned by docs_search), e.g. "twig/data" or "site-builder/overview".
輸入結構描述
{
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Documentation page path from docs_search results"
}
},
"required": [
"path"
]
}輸出結構描述
{
"type": "object",
"oneOf": [
{
"type": "object",
"required": [
"error"
],
"additionalProperties": false,
"properties": {
"error": {
"type": "string"
}
}
},
{
"type": "object",
"required": [
"path",
"title",
"group",
"markdown"
],
"additionalProperties": false,
"properties": {
"path": {
"type": "string"
},
"title": {
"type": "string"
},
"group": {
"type": "string"
},
"markdown": {
"type": "string"
}
}
}
]
}🟢docs_lookup(kind, name)
Look up a specific Total CMS reference entry: Twig functions/filters, field types, REST API endpoints, schema configuration keys, CLI commands, extension API, or builder API. Omit `name` to list all entries of a kind.
輸入結構描述
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"twig_function",
"twig_filter",
"field_type",
"api_endpoint",
"schema_config",
"cli_command",
"extension_api",
"builder_api"
]
},
"name": {
"type": "string",
"description": "Entry name (function name, field type, \"GET /api/collections\", command name…). Omit to list the kind."
}
},
"required": [
"kind"
]
}輸出結構描述
{
"type": "object",
"oneOf": [
{
"type": "object",
"required": [
"error"
],
"additionalProperties": false,
"properties": {
"error": {
"type": "string"
}
}
},
{
"type": "object",
"required": [
"kind",
"names",
"total"
],
"additionalProperties": false,
"properties": {
"kind": {
"type": "string"
},
"names": {
"type": "array",
"items": {
"type": "string"
}
},
"total": {
"type": "integer"
}
}
},
{
"type": "object",
"required": [
"kind",
"entry"
],
"additionalProperties": false,
"properties": {
"kind": {
"type": "string"
},
"entry": {
"description": "The matched reference entry. Shape varies by kind — see this method's docblock."
},
"topic": {
"type": "string",
"description": "Present only for extension_api/builder_api item-level matches — the topic key the match was found under."
},
"match": {
"type": "string",
"description": "Present only for extension_api/builder_api item-level matches — the matched identity string."
}
}
},
{
"type": "object",
"required": [
"kind",
"candidates",
"hint"
],
"additionalProperties": false,
"properties": {
"kind": {
"type": "string"
},
"candidates": {
"type": "array",
"items": {
"description": "Either a raw reference entry (listed kinds) or {topic, match, entry} (keyed kinds) — see this method's docblock."
}
},
"hint": {
"type": "string"
}
}
}
]
}🟢docs_search(query, limit)
Search the Total CMS documentation. Returns matching pages with their path, title, group, and section headings. Use docs_get with a returned path to read the full page.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search terms, e.g. \"image resize twig\" or \"webhook automation\""
},
"limit": {
"type": "integer",
"description": "Maximum results (default 8, max 20)"
}
},
"required": [
"query"
]
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"path",
"title",
"group",
"sections"
],
"additionalProperties": false,
"properties": {
"path": {
"type": "string"
},
"title": {
"type": "string"
},
"group": {
"type": "string"
},
"sections": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
},
"message": {
"type": "string",
"description": "Present only when the query was too short (no token of 2+ characters). No `total`/`hint` alongside it."
},
"total": {
"type": "integer",
"description": "Present when a search actually ran — total matches before the limit was applied."
},
"hint": {
"type": "string",
"description": "Present when a search actually ran — guidance for the next call."
}
},
"required": [
"results"
],
"additionalProperties": false
}🟢fetch(id)
Fetch the full document for a search result id. Returns {id, title, text, url, metadata}; `text` is the readable body for citation. Pass an id returned by the `search` tool.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "A document id returned by the `search` tool."
}
},
"required": [
"id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object"
}
},
"required": [
"id",
"title",
"text",
"url"
],
"additionalProperties": true
}🟢find_comparison(competitor)
Find the head-to-head comparison page for a competitor by name (case-insensitive partial match). Returns the full page content including the feature table. Parameters: - competitor (string, required): Competitor name, e.g. "Kirby" or "Craft". Returns: paginated comparisons objects with url per item.
輸入結構描述
{
"type": "object",
"properties": {
"competitor": {
"type": "string",
"description": "Competitor name, e.g. \"Kirby\" or \"Craft\"."
}
},
"required": [
"competitor"
]
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matching comparisons objects, each decorated with a `url` field where the collection has a public URL pattern configured. Field set varies by collection — call describe_collection for the schema.",
"items": {
"type": "object",
"additionalProperties": true,
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
}
}
},
"total": {
"type": "integer",
"description": "Total matching items (post-persona-filter)."
},
"limit": {
"type": "integer",
"description": "Cap applied to this response — server may have lowered the requested limit."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean",
"description": "True when total > offset + count(items); call again with offset += limit to paginate."
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢get_object(collection, id, format, locale)
Fetch a single object by its id from a collection. Returns the full object as a flat map of fields, decorated with a `url` field where the collection has a public URL pattern configured. This tool does not search or filter — use query_collection for paginated lists or search_collection for free-text search. Available collections and filterable properties: - articles — id (id, sortable), title (text), author (select), summary (textarea), date (date, sortable), draft (toggle), updated (datetime, sortable) - comparisons — competitor (text), competitorUrl (url), heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - extension — id (id, sortable), name (text), extensionId (text), soldAs (text), summary (textarea), category (select), price (number, sortable), currency (select), minEdition (select), minVersion (text), bundled (toggle), beta (toggle), docsUrl (url), productUrl (url), draft (toggle), owner (select), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable) - releases — id (id, sortable), version (text), title (text), date (date, sortable), draft (toggle), urgent (toggle), fullnotesurl (url), announce (toggle) - roundups — heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - showcase — name (text), url (url), industry (select), id (id, sortable), owner (select), draft (toggle), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable)
輸入結構描述
{
"type": "object",
"properties": {
"collection": {
"type": "string",
"description": "Collection id. Use list_collections to discover available collections.",
"examples": [
"blog",
"products"
]
},
"id": {
"type": "string",
"description": "Object id (slug). Get candidate ids from query_collection or search_collection output.",
"examples": [
"hello-world",
"fall-collection-2025"
]
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Rendered format for content fields. Accepted now for forward-compat; full conversion ships with the Tiptap→markdown converter in a later release."
},
"locale": {
"type": "string",
"default": "",
"description": "BCP 47 locale tag. Accepted for forward-compat with the 3.6 i18n release — has no effect today."
}
},
"required": [
"collection",
"id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Object id (slug)."
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
},
"required": [
"id"
],
"additionalProperties": true
}🟢get_resource(uri)
Resolve a tcms:// resource URI to its underlying object. Format: tcms://{collection}/{id} — e.g. tcms://blog/hello-world. Equivalent to calling get_object with the parsed collection and id; returns the same shape. Use this when a URI has been surfaced to you (in other tool output, in user input, etc.); use get_object directly when you have a separate collection + id pair. Extension-registered URIs (other schemes) are reachable via the resources/read transport surface.
輸入結構描述
{
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "A tcms:// resource URI identifying one object. Format: tcms://{collection}/{id}.",
"examples": [
"tcms://blog/hello-world",
"tcms://products/fall-collection-2025"
]
}
},
"required": [
"uri"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Object id (slug)."
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
},
"required": [
"id"
],
"additionalProperties": true
}🟢get_view(id, format, locale)
Fetch a data view's full cached result by id. Output is freeform — each item's field set depends on the view's Twig definition. Call describe_view first to learn the expected shape. Capped at 50 items; larger views return the first 50 plus a hint to call query_view for pagination. For per-item paginated access use query_view directly.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "View id. Use list_views to discover available views.",
"examples": [
"recent-posts",
"monthly-sales-summary"
]
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Forward-compat with collection tools. View data is freeform so this has no effect today."
},
"locale": {
"type": "string",
"default": "",
"description": "BCP 47 locale tag — forward-compat for the 3.6 i18n release. No effect today."
}
},
"required": [
"id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Items produced by the view, capped at 50. Field set varies by view — call describe_view for the expected shape.",
"items": {
"type": "object",
"additionalProperties": true
}
},
"total": {
"type": "integer",
"description": "Total cached items in the view (pre-cap)."
},
"truncated": {
"type": "boolean",
"description": "True when total > 50; pair with query_view for full pagination."
},
"hint": {
"type": "string",
"description": "Present only when truncated — points the agent at query_view."
}
},
"required": [
"items",
"total",
"truncated"
],
"additionalProperties": true
}🟢latest_release
The most recent Total CMS release: version, title, date and the release summary. Returns: paginated releases objects with url per item.
輸入結構描述
{
"type": "object",
"properties": {}
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matching releases objects, each decorated with a `url` field where the collection has a public URL pattern configured. Field set varies by collection — call describe_collection for the schema.",
"items": {
"type": "object",
"additionalProperties": true,
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
}
}
},
"total": {
"type": "integer",
"description": "Total matching items (post-persona-filter)."
},
"limit": {
"type": "integer",
"description": "Cap applied to this response — server may have lowered the requested limit."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean",
"description": "True when total > offset + count(items); call again with offset += limit to paginate."
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢list_collections
Discover the collections visible to you. Lean overview — one entry per collection. Returns id, name (display label), schema (the schema id this collection uses), description, url_pattern, access level, and total_objects (so you can decide whether to paginate or enumerate). For the per-property detail of one collection (which properties exist, which are filterable/sortable), call describe_collection. Then query_collection / search_collection / get_object for the data.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"collections": {
"type": "array",
"description": "Persona-filtered list, sorted alphabetically by id.",
"items": {
"type": "object",
"required": [
"id",
"name",
"schema",
"access",
"total_objects"
],
"additionalProperties": false,
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string",
"description": "Display label, falls back to id."
},
"schema": {
"type": "string",
"description": "Schema id this collection uses."
},
"description": {
"type": [
"string",
"null"
],
"description": "Resolved mcp.description, falling back to the schema description."
},
"url_pattern": {
"type": "string",
"description": "URL template for objects, e.g. \"/blog/{id}\". Empty string when no pattern is configured."
},
"access": {
"type": "string",
"enum": [
"admin",
"apikey",
"authenticated",
"public"
]
},
"total_objects": {
"type": "integer"
}
}
}
},
"total": {
"type": "integer",
"description": "Number of collections in the response (post-persona-filter)."
}
},
"required": [
"collections",
"total"
],
"additionalProperties": false
}🟢list_guides
The site's Guides: evergreen buying-guide pages served at /guides/{id}, stored in the roundups collection. Returns every guide in display order with its id, heading, lede, reviewed date and draft flag. A guide's full content (contenders, choose, howToChoose, faqs, sources) is on the object itself: get_object with collection "roundups". Returns: paginated roundups objects with url per item.
輸入結構描述
{
"type": "object",
"properties": {}
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matching roundups objects, each decorated with a `url` field where the collection has a public URL pattern configured. Field set varies by collection — call describe_collection for the schema.",
"items": {
"type": "object",
"additionalProperties": true,
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
}
}
},
"total": {
"type": "integer",
"description": "Total matching items (post-persona-filter)."
},
"limit": {
"type": "integer",
"description": "Cap applied to this response — server may have lowered the requested limit."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean",
"description": "True when total > offset + count(items); call again with offset += limit to paginate."
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢list_views
Discover the pre-computed data views visible to you. Lean overview — one entry per view. Data views are Twig-defined queries that aggregate across collections; their result is cached and accessible by id. Returns id, name, description, last_built, and access. Use the id with query_view (paginated query), get_view (fetch the whole cached result), or describe_view (output shape + metadata). For raw collection content use list_collections instead.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"views": {
"type": "array",
"description": "Persona-filtered list, sorted alphabetically by id.",
"items": {
"type": "object",
"required": [
"id",
"name",
"access"
],
"additionalProperties": false,
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"last_built": {
"type": "string",
"description": "ISO 8601 timestamp of the last successful build, empty string when never built."
},
"access": {
"type": "string",
"enum": [
"admin",
"apikey",
"authenticated",
"public"
]
}
}
}
},
"total": {
"type": "integer"
}
},
"required": [
"views",
"total"
],
"additionalProperties": false
}🟢needs_review(before)
Comparison pages ordered by how long ago their competitor facts were last verified, oldest first. Pass `before` (ISO date) to return only pages last verified before that date. Each page shows its verification date publicly, so keeping these fresh matters. Parameters: - before (string, optional): Only pages whose reviewed date is on or before this ISO date (optional). Returns: paginated comparisons objects with url per item.
輸入結構描述
{
"type": "object",
"properties": {
"before": {
"type": "string",
"description": "Only pages whose reviewed date is on or before this ISO date (optional).",
"format": "date"
}
}
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matching comparisons objects, each decorated with a `url` field where the collection has a public URL pattern configured. Field set varies by collection — call describe_collection for the schema.",
"items": {
"type": "object",
"additionalProperties": true,
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
}
}
},
"total": {
"type": "integer",
"description": "Total matching items (post-persona-filter)."
},
"limit": {
"type": "integer",
"description": "Cap applied to this response — server may have lowered the requested limit."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean",
"description": "True when total > offset + count(items); call again with offset += limit to paginate."
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢query_collection(collection, include, exclude, sort, limit, ...)
Query a collection for paginated content. Returns the matching items plus pagination metadata (total, limit, offset, has_more); each item is decorated with a public `url` field where one is configured. Use REST-style `include` / `exclude` filter strings (comma-separated field:value pairs; AND-semantics for include, OR-semantics for exclude) and `sort` (e.g. `date:desc`). Only properties listed in the catalog below are queryable — other schema properties exist on objects but are not filterable here; use get_object if you need the full record or describe_collection to see every property. This tool does not free-text search content — use search_collection for that. It does not fetch a single object by id — use get_object. Available collections and filterable properties: - articles — id (id, sortable), title (text), author (select), summary (textarea), date (date, sortable), draft (toggle), updated (datetime, sortable) - comparisons — competitor (text), competitorUrl (url), heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - extension — id (id, sortable), name (text), extensionId (text), soldAs (text), summary (textarea), category (select), price (number, sortable), currency (select), minEdition (select), minVersion (text), bundled (toggle), beta (toggle), docsUrl (url), productUrl (url), draft (toggle), owner (select), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable) - releases — id (id, sortable), version (text), title (text), date (date, sortable), draft (toggle), urgent (toggle), fullnotesurl (url), announce (toggle) - roundups — heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - showcase — name (text), url (url), industry (select), id (id, sortable), owner (select), draft (toggle), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable)
輸入結構描述
{
"type": "object",
"properties": {
"collection": {
"type": "string",
"description": "Collection id (slug-form). Use list_collections to discover available collections.",
"examples": [
"blog",
"products",
"team"
]
},
"include": {
"type": "string",
"default": "",
"description": "Comma-separated field:value pairs items must ALL match. Wildcards \"*foo*\", \"foo*\", \"*foo\" supported.",
"examples": [
"featured:true",
"category:tech,published:true"
]
},
"exclude": {
"type": "string",
"default": "",
"description": "Comma-separated field:value pairs that exclude items (OR). Drafts the caller may not see are removed before this filter runs, whatever it says.",
"examples": [
"draft:true",
"status:archived,featured:false"
]
},
"sort": {
"type": "string",
"default": "",
"description": "Sort rule \"field:direction\"; multiple rules comma-separated. Only fields marked sortable in the catalog will sort.",
"examples": [
"date:desc",
"title:asc"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Maximum items to return. Capped at 50 (vs. REST's 100) to fit MCP response-size budgets."
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Number of items to skip — combine with limit for pagination."
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Rendered format for content fields. Accepted now for forward-compat; full conversion ships with the Tiptap→markdown converter in a later release."
},
"locale": {
"type": "string",
"default": "",
"description": "BCP 47 locale tag. Accepted for forward-compat with the 3.6 i18n release — has no effect today."
}
},
"required": [
"collection"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matching objects in sort order. Field set varies by collection — call describe_collection for the schema.",
"items": {
"type": "object",
"additionalProperties": true,
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string",
"description": "Public URL for this object when the collection has a URL pattern configured."
}
}
}
},
"total": {
"type": "integer",
"description": "Total matching items (post-persona-filter)."
},
"limit": {
"type": "integer",
"description": "Cap applied to this response — server may have lowered the requested limit."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean",
"description": "True when total > offset + count(items); call again with offset += limit to paginate."
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢query_view(id, include, exclude, sort, limit, ...)
Paginated query against a data view's cached result. REST-syntax include/exclude/sort, same vocabulary as query_collection. View data is freeform — call describe_view first to learn the field set before composing filters. `limit` is capped at 50; use offset to paginate larger views.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "View id from list_views.",
"examples": [
"recent-posts",
"monthly-sales-summary"
]
},
"include": {
"type": "string",
"description": "REST-style filter, e.g. \"category:tech,published:true\". Field names depend on the view's output shape.",
"examples": [
"featured:true",
"year:2025"
]
},
"exclude": {
"type": "string",
"description": "REST-style negative filter.",
"examples": [
"draft:true"
]
},
"sort": {
"type": "string",
"description": "Sort spec, e.g. \"date:desc\"."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Forward-compat with query_collection; no effect today since view data is freeform."
},
"locale": {
"type": "string",
"default": "",
"description": "Forward-compat for 3.6 i18n."
}
},
"required": [
"id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Items in the requested page. Field set varies by view; call describe_view for the shape.",
"items": {
"type": "object",
"additionalProperties": true
}
},
"total": {
"type": "integer"
},
"limit": {
"type": "integer",
"description": "Effective cap applied to this response."
},
"offset": {
"type": "integer"
},
"has_more": {
"type": "boolean"
}
},
"required": [
"items",
"total",
"limit",
"offset",
"has_more"
],
"additionalProperties": false
}🟢search(query)
Search site content across all collections you can see. Returns matching results as {id, title, url}; pass a result id to `fetch` to read the full document. Drafts are hidden from anonymous callers.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search terms."
}
},
"required": [
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"title",
"url"
],
"additionalProperties": false,
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
}
}
}
},
"required": [
"results"
]
}🟢search_collection(collection, query, limit, format, locale)
Free-text search within a single collection. Returns matching items decorated with a public `url`; total reflects what was found. Supports AND (default), OR, and "quoted phrases". Searches across the properties listed in the catalog below — other schema properties exist on objects but are not searchable here; use get_object for the full record or describe_collection to see every property. This tool does not filter by field value — use query_collection with `include`/`exclude` for that. Drafts are auto-hidden from anonymous callers. Available collections and filterable properties: - articles — id (id, sortable), title (text), author (select), summary (textarea), date (date, sortable), draft (toggle), updated (datetime, sortable) - comparisons — competitor (text), competitorUrl (url), heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - extension — id (id, sortable), name (text), extensionId (text), soldAs (text), summary (textarea), category (select), price (number, sortable), currency (select), minEdition (select), minVersion (text), bundled (toggle), beta (toggle), docsUrl (url), productUrl (url), draft (toggle), owner (select), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable) - releases — id (id, sortable), version (text), title (text), date (date, sortable), draft (toggle), urgent (toggle), fullnotesurl (url), announce (toggle) - roundups — heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable) - showcase — name (text), url (url), industry (select), id (id, sortable), owner (select), draft (toggle), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable)
輸入結構描述
{
"type": "object",
"properties": {
"collection": {
"type": "string",
"description": "Collection id to search within. Use list_collections to discover available collections.",
"examples": [
"blog",
"products"
]
},
"query": {
"type": "string",
"description": "Search terms. AND-semantics by default; use `or` between terms for OR; wrap phrases in double quotes.",
"examples": [
"rust performance",
"\"static analysis\"",
"php or python"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Maximum items to return (capped at 50 to fit MCP response-size budgets)."
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Output format for styledtext properties on the matched items. markdown is friendliest for AI consumption."
},
"locale": {
"type": "string",
"default": "",
"description": "BCP 47 locale tag. Accepted for forward-compat with the 3.6 i18n release — has no effect today."
}
},
"required": [
"collection",
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matched objects, each a flat field map decorated with a `url`. Field set varies by collection.",
"items": {
"type": "object",
"additionalProperties": true,
"properties": {
"id": {
"type": "string",
"description": "Object id (slug)."
},
"url": {
"type": "string",
"description": "Public URL when the collection has a URL pattern."
}
}
}
},
"total": {
"type": "integer",
"description": "Number of items returned."
},
"limit": {
"type": "integer",
"description": "Applied result cap."
},
"query": {
"type": "string",
"description": "The query that was run."
}
},
"required": [
"items",
"total",
"limit",
"query"
],
"additionalProperties": false
}🟢search_collections(query, limit, format, locale)
Full-text search across every collection you can see, in one call. Returns matching items each decorated with `collection` (which collection the hit came from) and `url`. Pair `collection` + `id` to fetch the full record via get_object. Call list_collections for the available collections and describe_collection on any one for its full property list; properties not flagged filterable there exist on objects but are not searched here (use get_object for the full record). For a single-collection search use search_collection instead — same query syntax, scoped tighter. Drafts are auto-hidden from anonymous callers.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search terms. AND-semantics by default; use `or` between terms for OR; wrap phrases in double quotes.",
"examples": [
"rust performance",
"\"static analysis\"",
"php or python"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Maximum items returned in aggregate across all collections. Capped at 50 for MCP response-size budgets."
},
"format": {
"type": "string",
"enum": [
"markdown",
"html",
"text"
],
"default": "markdown",
"description": "Output format for styledtext properties on the matched items. markdown is friendliest for AI consumption."
},
"locale": {
"type": "string",
"default": "",
"description": "BCP 47 locale tag. Accepted for forward-compat with the 3.6 i18n release — has no effect today."
}
},
"required": [
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"items": {
"type": "array",
"description": "Matched objects across collections, each a flat field map decorated with `collection` (the source collection id) and `url`. Field set varies by collection.",
"items": {
"type": "object",
"additionalProperties": true,
"properties": {
"id": {
"type": "string",
"description": "Object id (slug)."
},
"collection": {
"type": "string",
"description": "Collection the hit came from. Pair with id for get_object."
},
"url": {
"type": "string",
"description": "Public URL when the collection has a URL pattern."
}
}
}
},
"total": {
"type": "integer",
"description": "Number of items returned in aggregate."
},
"limit": {
"type": "integer",
"description": "Applied aggregate result cap."
},
"query": {
"type": "string",
"description": "The query that was run."
}
},
"required": [
"items",
"total",
"limit",
"query"
],
"additionalProperties": false
}社群
證據