Build with AI

Large language models were trained before the latest version of ImageKit, so on their own they often suggest outdated API signatures, invent transformation parameters, or pick the wrong approach. The tools on this page fix that. They give your AI assistant accurate, up-to-date knowledge of ImageKit and the ability to act on your account.

There are three ways to use AI with ImageKit:

What you want to do	Use this	Best for
Let an AI assistant work in your account, so it can search, upload, tag, organize, and share media, or manage origins, URL endpoints, and usage from natural language	MCP servers	Ops automation, content teams, and agentic workflows
Help your AI assistant integrate ImageKit and build transformations correctly as you code	Agent skills	Developers integrating ImageKit in an IDE such as Cursor, VS Code, Windsurf, Claude Code, or Codex
Give any AI assistant the full ImageKit documentation in a single, plain-text file	Plain text docs	Helping any AI assistant answer from the latest ImageKit docs, including ChatGPT and Claude

If you are building in an IDE, the quickest way to get everything is to install the ImageKit skills, then add the MCP servers for your client.

Install

ImageKit skills teach your AI coding agent how to use ImageKit's MCP servers correctly. Each skill is a playbook for a task the tool schema does not make obvious — searching the library, uploading, sharing, building a transformation, or querying the docs.

Every IDE installs the skills with the same command:

Copy

npx skills add imagekit-developer/skills --all

Then add the MCP servers shown for your tool. DAM and Admin require you to sign in to ImageKit and grant access the first time you connect. DevTools needs no authentication.

VS Code Copilot

Claude Code

Claude Desktop & Claude.ai (web)

Cursor

Windsurf

Codex

What you get

Skill	What it does
mcp-preflight	Which MCP server to call: DAM (media library), Admin (origins, URL endpoints, usage analytics), or DevTools.
search-assets	Lucene `searchQuery` for searching the media library, including discovering custom metadata fields and tags before guessing.
upload-files	Uploads via the DAM picker or a signed upload. Never inlines file bytes into the conversation.
asset-access-control	File/folder vs media-collection access tools, and the write rules that are easy to get wrong.
ai-tasks	Payload shape for AI tagging, metadata extraction, and quality checks on DAM assets.
search-docs	Teaches the agent to search official ImageKit docs, API references, SDKs, and community posts instead of relying on stale training data.
transformation-builder	Turns natural-language requests ("resize to 800x600 and crop to the face") into correct transformation URLs, including AI edits, background removal, generative fill, upscaling, and overlays.
imagekit-integrations	An index of ImageKit SDKs, plugins, and widgets across front-end, back-end, mobile, CMS, storage, video, and uploads, so the agent picks the right one before searching the docs.

MCP servers

The Model Context Protocol (MCP) is an open standard that lets AI assistants securely connect to external tools and data. ImageKit provides hosted, remote MCP servers, so there is no local server to run or maintain. Add them to any MCP client using the URLs below.

Server	URL	Authentication
DAM	`https://imagekit.io/mcp/dam`	Sign in with your ImageKit account
Admin	`https://imagekit.io/mcp/admin`	Sign in with your ImageKit account
DevTools	`https://devtools-mcp.imagekit.io/mcp`	None

If you previously connected https://api-mcp.imagekit.io/mcp, remove that server from your client and add DAM and Admin instead.

DAM MCP

The DAM MCP server lets an AI assistant work in your ImageKit media library on your behalf, with the same access as your user account. Connect to it at https://imagekit.io/mcp/dam.

It can:

Search and browse files and folders, including by tags, path, dates, and custom metadata.
Upload files from your computer (in clients that support interactive MCP Apps) or from a public URL.
Download files and create ZIP archives.
Organize files and folders: copy, move, rename, delete, publish, and bulk-update tags and metadata.
Manage custom metadata fields, path policies, and saved extensions.
Work with media collections, public links, file versions, and access control.
List and delete AI-generated images.
Purge CDN cache.

In supporting clients, search, upload, and file details can open an interactive UI with thumbnails and a file picker instead of plain JSON.

On first connect, you sign in to ImageKit and choose what the assistant is allowed to do. See security recommendations.

Admin MCP

The Admin MCP server lets an AI assistant manage account-level delivery settings and inspect usage. Connect to it at https://imagekit.io/mcp/admin.

It can:

List, create, update, and delete origins (external storage).
List, create, update, and delete URL endpoints.
View account usage totals and usage analytics.

On first connect, you sign in to ImageKit and grant access.

DevTools MCP

The DevTools MCP server makes any AI assistant better at ImageKit, even before you connect your account. It is public and needs no authentication, so you can connect to it at https://devtools-mcp.imagekit.io/mcp. It exposes two tools:

search_docs answers "how do I…" questions from official ImageKit docs, API references, SDK examples, and community posts, so the assistant works from real documentation instead of stale training data.
transformation_builder turns natural-language requests into correct transformation URLs, including AI transformations, background removal, generative fill, upscaling, smart cropping, and overlays.

Security recommendations

The DAM and Admin MCP servers are hosted and maintained by ImageKit. You sign in with your ImageKit account; the assistant never sees your password or API keys.

What the assistant can do is limited by:

The permissions you grant on the consent screen (for example, view the media library, but not delete).
Your current user role and DAM permissions. A restricted user can only act on files, folders, and collections shared with them, just as in the dashboard.

Grant only the access you need. View is enough for search and browse. Creating, updating, and deleting are required for uploads, edits, sharing, and destructive operations.

How authentication works

On first connect, ImageKit shows a consent screen so you can choose what the assistant can access:

Initial connection. On first connect, your MCP client redirects you to ImageKit at https://imagekit.io.
Sign in. You authenticate with your ImageKit account, the same way you open the dashboard.
Choose permissions. You review and approve what the assistant can do. Anything your role cannot grant is shown as unavailable.
Tied to your account. Access is bound to your user and the ImageKit account you signed into. Connect DAM for media library work and Admin for origins, URL endpoints, and usage — they are separate connections.
Ask again if needed. If the assistant later needs more access, you will be prompted to approve it.
Revoke anytime. Connected clients appear on your user profile. Revoke a grant there to cut off access immediately.

Best practices

Grant least privilege. Start with view access. Add create, update, or delete only when the workflow needs it.
Use the right ImageKit user. Connect MCP as a user whose role matches the work, not as an account administrator, unless you need that access.
Review actions. Keep a human in the loop for destructive operations such as bulk delete, access-control changes, or cache purge.
Revoke unused grants. Remove MCP clients you no longer use from your user profile.

Plain text docs

You can read any ImageKit documentation page as plain-text Markdown by adding .md to its URL. For example, the plain-text version of this page is at https://imagekit.io/docs/build-with-ai.md. You can also use the Copy page option at the top of any page.

This helps AI tools consume our content, and it lets you paste a whole doc into an LLM. Plain text is better than scraped HTML because it contains fewer formatting tokens, includes content hidden in the default view (such as text inside a tab or accordion), and preserves a Markdown hierarchy that LLMs can parse.

We also host an /llms.txt file, an emerging standard that indexes every page and links to its plain-text version. For everything in one request, /llms-full.txt concatenates the entire documentation into a single file. Point any AI agent at these so it answers from the latest ImageKit documentation instead of stale training data.

Troubleshooting

If an MCP client fails to connect:

Confirm the server URL is https://imagekit.io/mcp/dam, https://imagekit.io/mcp/admin, or https://devtools-mcp.imagekit.io/mcp. There is no local or self-hosted MCP server to install.
Complete the ImageKit sign-in and consent flow in the browser window the client opens. The consent URL starts with https://imagekit.io.
If you previously connected https://api-mcp.imagekit.io/mcp, remove it from your client and add DAM and Admin instead.
Restart your MCP client and try connecting again.

For more help, contact ImageKit support.