Blender integration through the Model Context Protocol
Cloudinary Analysis is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'CLOUDINARY_CLOUD_NAME=${CLOUDINARY_CLOUD_NAME}' --env 'CLOUDINARY_API_KEY=${CLOUDINARY_API_KEY}' --env 'CLOUDINARY_API_SECRET=${CLOUDINARY_API_SECRET}' --transport stdio cloudinary-analysis-mcp '--' npx -y @cloudinary/analysis-mcp
# 2 — ask your agent for something these tools do
# list_tools, describe_tool_input, execute_tool and 17 more
It needs CLOUDINARY_CLOUD_NAME, CLOUDINARY_API_KEY, CLOUDINARY_API_SECRET: this reads them from your environment, so export them first. Remote: OAuth sign-in · Package: API key.
Cloudinary Analysis costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads CLOUDINARY_CLOUD_NAME (Your Cloudinary cloud name. Find it in your Cloudinary Dashboard), CLOUDINARY_API_KEY (Your Cloudinary API key. Found in Dashboard > Settings > Access Keys), CLOUDINARY_API_SECRET (Your Cloudinary API secret. Found in Dashboard > Settings > Access Keys) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx CLOUDINARY_CLOUD_NAME …, setx CLOUDINARY_API_KEY …, setx CLOUDINARY_API_SECRET … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'CLOUDINARY_CLOUD_NAME=${CLOUDINARY_CLOUD_NAME}' --env 'CLOUDINARY_API_KEY=${CLOUDINARY_API_KEY}' --env 'CLOUDINARY_API_SECRET=${CLOUDINARY_API_SECRET}' --transport stdio cloudinary-analysis-mcp '--' npx -y @cloudinary/analysis-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://analysis.mcp.cloudinary.com/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http cloudinary-analysis-mcp https://analysis.mcp.cloudinary.com/mcpIt reaches a system of yours, so it needs your own credential rather than the publisher’s: CLOUDINARY_CLOUD_NAME — Your Cloudinary cloud name. Find it in your Cloudinary Dashboard.; CLOUDINARY_API_KEY — Your Cloudinary API key. Found in Dashboard > Settings > Access Keys.; CLOUDINARY_API_SECRET — Your Cloudinary API secret. Found in Dashboard > Settings > Access Keys.. You set them in your own client’s config, on your machine — this marketplace never holds it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List available tools. Optionally filter by search terms that match against tool name, description, and scopes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search_terms | array | no | — |
Get the input schema for one or more tools. It is a good idea to call this tool first to understand how to successfully call execute_tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool_names | array | yes | — |
Execute a tool by name with its arguments. If executing a given tool for the first time, it is recommended to call describe_tool_input first to understand the expected arguments shape.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | The name of the tool to execute |
| arguments | object | no | — |
No parameter schema on file.
Analyze - AI Vision General The General mode serves a wide array of applications by providing detailed answers to diverse questions about an image. Users can inquire about any aspect of an image, such as identifying objects, understanding scenes, or interpreting text within the image.
No parameter schema on file.
Analyze - AI Vision Moderation The Moderation mode accepts multiple questions about an image, to which the response provides concise answers of "yes," "no," or "unknown." This functionality allows for a nuanced evaluation of whether the image adheres to specific content policies, creative specs,…
No parameter schema on file.
Analyze - AI Vision Tagging The Tagging mode accepts a list of tag names along with their corresponding descriptions. If the image matches the description, which may encompass various elements, it will be appropriately tagged. This approach enables customers to align with their own brand…
No parameter schema on file.
Analyze - Captioning Provides a caption for an image.
No parameter schema on file.
Analyze - Cld-Fashion Analyze an image using the [Cld-Fashion](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's fashion model is specifically dedicated to items of clothing. The response includes…
No parameter schema on file.
Analyze - Cld-Text Analyze an image using the [Cld-Text](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's text model tells you if your image includes text, and where it's located. Used with image…
No parameter schema on file.
Analyze - Coco Analyze an image using the [Coco](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [Common Objects in Context](https://cocodataset.org/) model contains just 80 common objects.
No parameter schema on file.
Analyze - Google Logo Detection Detects popular product logos within an image.
No parameter schema on file.
Analyze - Google Tagging Provides tags for an image using Google's tagging service.
No parameter schema on file.
Analyze - Human Anatomy Analyze an image using the [Human Anatomy](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's human anatomy model identifies parts of the human body in an image. It works best…
No parameter schema on file.
Analyze - Image Quality Analysis Analyze an image using the [Image Quality Analysis](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#image_quality_analysis) model.
No parameter schema on file.
Analyze - Lvis Analyze an image using the [Lvis](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [Large Vocabulary Instance Segmentation](https://www.lvisdataset.org/) model contains thousands of general…
No parameter schema on file.
Analyze - Shop Classifier Analyze an image using the [Shop Classifier](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's shop classifier model detects if the image is a product image taken in a studio,…
No parameter schema on file.
Analyze - Unidet Analyze an image using the [Unidet](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [UniDet](https://github.com/xingyizhou/UniDet) model is a unified model, combining a number of object…
No parameter schema on file.
Analyze - Watermark Detection Analyze an image using the [Watermark Detection](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#watermark_detection) detection model.
No parameter schema on file.
Get analysis task status Get the status of an analysis task.
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Cloudinary Analysis or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (4 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 4 recovered tools are registered only when mcpScopes.length > 0 holds (esm/mcp-server/tools.js:273) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 3.
src/mcp-server/scopes.ts (1 KB) was not read: over the file-count budget.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
3 tools are registered unconditionally · 1 more only when mcpScopes.length > 0 holds (esm/mcp-server/tools.js:273) — typically when a key or option is configured. All 4 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_tools | no tags | |
| describe_tool_input | no tags | |
| execute_tool | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| list_scopes conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.5.3. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Cloudinary Analysis can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.