Cloudinary connector

Get image assets Retrieves a list of image assets. Results can be filtered by various criteria like tags, prefix, or specific public IDs.

Retrieves a list of tags currently applied to assets in your Cloudinary account Retrieves a comprehensive list of all tags that exist in your product environment for assets of the specified type. [Cloudinary Admin API documentation](https://cloudinary.com/documentation/admin_api)

Get video assets Retrieves a list of video assets. Results can be filtered by various criteria like tags, prefix, or specific public IDs.

Provides a powerful query interface to filter and retrieve assets and their details Returns a list of resources matching the specified search criteria. Uses a Lucene-like query language to filter assets by descriptive attributes (`public_id`, `asset_id`, `filename`, `display_name`, `folder` / `asset_folder`, `tags`, `context.<key>`), file details (`resource_type`, `type`, `format`, `bytes`, `width`, `height`, `duration`, `pages`, `aspect_ratio`, `transparent`, `grayscale`), lifecycle dates (`uploaded_at`, `created_at`, `taken_at`, `updated_at`, `last_updated.<kind>`), moderation and lifecycle state (`status`, `moderation_status`, `moderation_kind`), embedded data (`image_metadata.*`), structured metadata (`metadata.<external_id>`), and analysis fields (`face_count`, `colors`, `quality_score`, `illustration_score`, `accessibility_analysis.*`). Supports sorting, aggregate counts, and complex boolean expressions. See the `expression` parameter for the full field reference. ## Expression syntax - **Match**: `field:value` (token match) or `field=value` (exact match). Examples: `tags:shirt`, `tags=cotton`. - **Comparisons**: `>`, `<`, `>=`, `<=` for numbers and dates. Example: `bytes>10000000`. - **Ranges**: `field:[from TO to]` inclusive, `field:{from TO to}` exclusive. Example: `width:{200 TO 1028}`. - **Booleans**: `AND`, `OR`, `NOT` (uppercase), or `+` (must), `-` (must not). `NOT` must appear between clauses — a bare leading `NOT` is a parse error; use `-field:value` to negate the first clause. Group with parentheses: `(shirt OR pants) AND clothes`. - **Wildcards**: trailing `*` only, for prefix match (`public_id:shoes_*`, `format:jp*`, `tags:shirt*`). Not supported on `folder`, `asset_folder`, `resource_type`, or `type`. Leading `*`, middle `*`, `?`, and bare `*` (`folder:*`, `context.alt:*`) are all parse errors — wildcards cannot be used as a "field is present" probe. - **Tokenized vs exact fields**: `tags`, `filename`, `display_name`, `context.<key>`, and `metadata.<id>` match on tokens split by whitespace and punctuation — `tags:analysis` matches the tag `full-analysis`. `public_id`, `folder`, `asset_folder`, and `format` match the whole value — `public_id:dog` will not match `dog_pldcwy`; use `public_id="dog_pldcwy"` (exact) or `public_id:dog*` (prefix). These exact-match fields still accept a trailing `*` for prefix match (except `folder` / `asset_folder`, where wildcards are ignored). - **Dates**: ISO-8601 in quotes (`uploaded_at>"2024-01-15"`, `created_at>"2026-01-01T00:00:00Z"`) or relative shorthand `Nh`, `Nd`, `Nw` (`uploaded_at>1d`, `created_at:[4w TO 1w]`). Send raw `<`/`>`, never HTML-escaped. - **Quoting**: wrap any value containing a space, colon, or other reserved character (`! ( ) { } [ ] ^ ~ ? \ = & < > |`) in double quotes, or escape each character with `\`. Examples: `tags:"service:mantels"`, `tags:"brand:openhaul"`, `aspect_ratio:"16:9"`, `folder:"My Folder"`. ## Common mistakes - No months or years shorthand. `1m` and `1y` are not supported; use ISO dates: `created_at>"2024-01-01"` or `created_at:["2024-01-01" TO "2024-04-01"]`. - Use `folder:` or `asset_folder:` (singular); `folders:`, `asset_folder_id:`, and other invented variants are not valid fields. Pass the exact folder name — wildcards do not apply here. - There is no "has any value" / presence probe. `folder:*`, `metadata.alt:*`, `context.key:*`, `tags:*`, and `-tags:*` are all parse errors. See *"Which assets have any value for `metadata.<id>`?"* under **Common tasks** for workarounds. - `NOT foo AND bar` is a parse error. Write it as `bar AND NOT foo` or `-foo AND bar`, and keep every `NOT` between two clauses (`a AND NOT b AND NOT c` is fine; `NOT b AND NOT c …` is not). - `public_id:dog` will not match `dog_pldcwy`. Use `public_id="dog_pldcwy"` (exact) or `public_id:dog*` (prefix). - `tags=service:mantels` fails because the unquoted colon is parsed as a field separator. Use `tags="service:mantels"` or `tags=service\:mantels`. - Do not HTML-escape operators. Send `uploaded_at<1h`, not `uploaded_at&lt;1h`. - Do not leave an operand empty (e.g. `tags: AND -tags:foo`). Omit the empty clause entirely. ## Tips - Set `max_results: 0` to return only `total_count` and `aggregations` without any resource payload — useful for counts and aggregation-only queries. - `total_count` is always present in the response; prefer it over running an aggregation just to get a count. - `aggregate` (both simple and range variants) and the `metadata`, `image_metadata`, `image_analysis` values of `with_field` require a Tier 2 search plan. - Range aggregations require each range to include a `key` label (1–20 chars, `[a-zA-Z0-9_-]+`) and at least one of `from` / `to`. ## Common tasks - **Count matching assets** — put the filter in `expression` with `max_results: 0` and read `total_count` from the response. Works on every tier; no `aggregate` needed. - **Preview one matching asset** — set `max_results: 1`; add `with_field: ["tags", "context"]` (or `metadata`, Tier 2) to inspect values. Prefer this over fetching and scanning a full page. - **Distribution of values for a field** — Tier 2: `aggregate: [format|resource_type|type]` for enum counts, or range aggregations on `bytes`, `image_pixels`, `video_pixels`, or `duration`. Tier 1 fallback: run N small queries with `max_results: 0`, one per candidate value, and read `total_count` from each. - **"Which assets have any value for `metadata.<id>`?"** — not expressible directly (`metadata.X:*` is a parse error; there is no presence probe). Workarounds: (a) if the field has a known value set, enumerate — `metadata.region:(apac OR emea OR amer)`; (b) query broadly with `with_field: ["metadata"]` (Tier 2) and filter client-side for entries where the field is set; (c) at ingest time, attach a sentinel tag whenever the field is set, then search by that tag. - **Newest / largest N** — keep the filter in `expression` and sort explicitly: `sort_by: [{uploaded_at: "desc"}]` with `max_results: 10`. - **Filter by folder** — both `asset_folder:"parent/child"` and `folder:"parent/child"` match an exact folder path; there is no wildcard or "contains". To query across multiple folders, enumerate: `asset_folder:("campaigns/2024" OR "campaigns/2025")`. - **Filter by metadata when you only know the label** — first call `list-metadata-fields` to resolve the label to an `external_id`, then query `metadata.<external_id>:value`. - **Multiple independent filters in one turn** — prefer one `expression` with `OR` / parentheses over firing many parallel calls: `metadata.region:apac OR metadata.region:emea` in a single request is faster and more reliable than two parallel requests. ## Examples - `tags:shirt AND uploaded_at>1d` - `resource_type:image AND bytes>1000000 AND (format:png OR format:jpg)` - `folder:products AND context.category:electronics` - `tags:"service:mantels" AND -tags:discontinued`

Searches for folders whose attributes match a given expression Lists the folders that match the specified search expression. Limited to 2000 results. If no parameters are passed, returns the 50 most recently created folders in descending order of creation time.

Finds images in your asset library based on visual similarity or content Returns a list of resources that are visually similar to a specified image. You can provide the source image for comparison in one of three ways: - Provide a URL of an image - Specify the asset ID of an existing image - Provide a textual description

Creates an archive (ZIP or TGZ file) that contains a set of assets from your product environment. Creates a downloadable ZIP or other archive format containing the specified resources.

Generate an image Generate an image from a text prompt using AI models. The model is selected via the optional `model` object: 1. If `model.id` is provided, use that exact model. 2. Else if `model.family` (+ optional `model.tier`) is provided, resolve via the model registry; a missing tier defaults to `standard`. 3. Else if `model.mode` is `auto`, the service picks the model for the request (optionally steered by `model.preference`). 4. Otherwise, use the global default (nano-banana / premium, i.e. `nano-banana-2`).

Generate an image from reference images Generate an image guided by one or more **reference images** — restyle, on-brand variants, character consistency, virtual try-on, edit/extend — steered by `prompt`. Only edit-capable models are selectable here. The model is selected via the optional `model` object, exactly like `text_to_image`, but IDs are restricted to edit models: 1. If `model.id` is provided, use that exact edit model. 2. Else if `model.family` (+ optional `model.tier`) is provided, resolve to that family's edit model (e.g. `nano-banana` / `premium` → `nano-banana-2-edit`). 3. Else if `model.mode` is `auto`, the service picks an edit model for the request (optionally steered by `model.preference`). 4. Otherwise, use the default edit model (`nano-banana-2-edit`). Each reference image is either a stored managed asset (by `asset_id`, read-permission checked) or an external HTTPS `url`.

Sets structured metadata values on multiple assets Assigns structured metadata field values to the given assets, addressing them by public ID. Values are merged into each asset's existing structured metadata: fields not mentioned keep their current values, and an empty value clears the field. Every referenced field must already exist in the product environment. Conditional metadata rules are evaluated as part of the update.

Adds, removes, or replaces tags on multiple assets Applies a tag command to the given assets, addressing them by public ID. The number of tags multiplied by the number of public IDs must not exceed 10,000.

Renames or moves an entire folder (along with all assets it contains) to a new location Renames or moves an entire folder (along with all assets it contains) to a new location within your Cloudinary media library.

Generate derived transformations for existing assets using Cloudinary's explicit API with eager transformations ⚠️ CRITICAL PREREQUISITES: 1. MUST call get-tx-reference tool first 2. MUST validate transformation syntax against official docs 3. MUST use only documented parameters from the reference 4. MUST follow proper URL component structure (slashes between components, commas within) 📋 VALIDATION CHECKLIST: - ✅ Called get-tx-reference tool - ✅ Verified all parameters exist in official docs - ✅ Used correct syntax (e.g., f_auto/q_auto not f_auto,q_auto) - ✅ Applied proper component chaining rules - ✅ Included crop mode when using width/height This tool creates actual derived assets on Cloudinary using the explicit API.

Uploads media assets (images, videos, raw files) to your Cloudinary product environment Uploads media assets (images, videos, raw files) to your Cloudinary product environment. The file is securely stored in the cloud with backup and revision history. Cloudinary automatically analyzes and saves important data about each asset, such as format, size, resolution, and prominent colors, which is indexed to enable searching on those attributes. Supports uploading from: - Local file paths (SDKs/MCP server only). For MCP server path MUST start with file:// - Remote HTTP/HTTPS URLs - Base64 Data URIs (max ~60 MB) - Private storage buckets (S3 or Google Storage) - FTP addresses The uploaded asset is immediately available for transformation and delivery upon successful upload. Transform media files using transformation syntax in delivery URLs, which creates derived files accessible immediately without re-uploading the original.