Cloudinary MCP connector
The Cloudinary connector lets Claude, ChatGPT, Cursor and the Elaichi Agent upload, search, organize and transform the images, videos and files in your Cloudinary product environment, with each person signed in as themselves.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Cloudinary to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Cloudinary once
-
Open Connections, choose Add connection, and pick Cloudinary.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Cloudinary. Cloudinary's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
Egnyte
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Cloudinary MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Cloudinary MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Cloudinary MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Cloudinary to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Cloudinary through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Marketing
Pull campaign images together in one ask
Ask for every image tagged with a campaign name and get the list back with folders and formats, ready to hand to the agency or drop into a brief.
-
Design
Upload and tag new assets from a chat
Send the latest hero images into the right Cloudinary folder, tag them for the launch, and have the agent confirm what landed where.
-
E-commerce
Resize product photos for every storefront
Ask for the square, banner and thumbnail versions of a product image and get the transformed URLs without opening Cloudinary.
-
Content
Find the video you half remember
Describe a video by subject, length or when it was uploaded and let the agent search Cloudinary and bring back the matches.
-
Web
Tidy folders before a site refresh
Move stale images into an archive folder, rename files to match the new page structure, and keep the live folders clean.
-
Brand
Check that assets carry the right tags
Ask which images in the brand folder are missing a usage tag or a region tag, then fix them in the same conversation.
Try asking
- “Find every product image tagged spring campaign in the marketing folder”
- “Upload these hero images to the homepage folder and tag them launch”
- “Which videos in the brand folder were added this week?”
Compare
Elaichi vs Zapier MCP vs Composio for Cloudinary
All three can connect Cloudinary to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Cloudinary tools | Allow or restrict single Cloudinary tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Cloudinary call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
See it in Elaichi
What connecting Cloudinary gets you
5 screens from the product, each doing one job for your Cloudinary account.
The agent
Ask about your Cloudinary assets in plain language.
Find images, videos and folders by asking, with answers drawn from live Cloudinary records.
- images
- videos
- folders
- tags
Ask Elaichi to work across your apps.
Find every product image tagged spring campaign in the marketing folder
Upload these hero images to the homepage folder and tag them launch
Which videos in the brand folder were added this week?
Also runs in Claude, ChatGPT or Cursor
MCP clients
Cloudinary works in every client through one endpoint.
Claude, ChatGPT and Cursor reach Cloudinary through one governed endpoint, no SDK, no shared API key.
Copy the endpoint
Toolboxes
Each team gets its own Cloudinary toolbox.
Marketing, Design and E-commerce each work from a toolbox scoped to their Cloudinary tasks.
- Marketing
- Design
- E-commerce
- Content
Shared connections
One Cloudinary connection, shared without sharing a credential.
See who connected each Cloudinary account and which teams and members work through it.
- Marketing
- Design
- E-commerce
- Content
Audit log
Every Cloudinary change is logged with a name.
When, who, what happened and which asset, in an append-only log you can search.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule runs the work, you approve it.
New Cloudinary uploads are fetched, grouped and drafted into a digest, approved, then posted back.
Cloudinary digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch images
Cloudinary
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Cloudinary
Queued
Collections and dashboards
Cloudinary health numbers arrive before anyone asks.
Four metrics, 14 days of uploads and a team breakdown, computed with no model involved.
Cloudinary health
Refreshed 4 minutes ago · every 15 minutes · from the images collection
Images
1,284 ↓ 12%
Videos
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Images created
Last 14 days
By team
Share of activity
Marketing 34%
Design 27%
E-commerce 21%
Content 18%
FAQ
Frequently asked questions
How do I connect Cloudinary to Claude?
Connect Cloudinary in Elaichi first: you sign in to your Cloudinary account over OAuth, and there is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste the Elaichi endpoint, https://api.elaichi.ai/mcp. From there Claude can work with the images, videos and folders your Cloudinary login already allows.
Does Cloudinary work with ChatGPT and Cursor as well as Claude?
Yes. Once Cloudinary is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, the Elaichi Agent and any other MCP client. You connect Cloudinary once and every client sees it.
What can an AI agent actually do with my Cloudinary assets?
An agent can upload images, videos and files into your Cloudinary folders, search for assets by tag, folder or name, move and rename them, and produce transformed versions such as a resized or cropped image. Short, concrete asks work best, such as asking for every image tagged with a campaign rather than describing the whole project. What is available depends on what your Cloudinary account has set up.
Does connecting Cloudinary give the AI access to my whole product environment?
No. Every call into Cloudinary runs as the person who signed in, so the agent sees only the folders and assets that person can already reach in Cloudinary. Elaichi can narrow that access further with roles and restrictions, but it can never widen it beyond what Cloudinary itself grants.
Can I stop an agent from deleting or changing things in Cloudinary?
Yes. Restrictions in Elaichi apply per action, so you can allow searching and uploading in Cloudinary while blocking deletes or renames. A restricted action is never advertised to Claude, ChatGPT or Cursor, so no prompt can reach it.
What happens to a Cloudinary connection when someone leaves?
Offboarding that person in Elaichi ends their access to Cloudinary through every client at once. A shared Cloudinary connection keeps working for everyone else on the team. If you later disconnect Cloudinary in Elaichi, it disappears from Claude, ChatGPT, Cursor and every other client in one step.
Does the Cloudinary MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Cloudinary is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Cloudinary?
Yes. Both let Claude, ChatGPT or Cursor use Cloudinary. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Cloudinary call.
How is Elaichi different from Composio for Cloudinary?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Cloudinary: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Cloudinary in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.