ImageKit MCP. Audit, patch, and purge media assets via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
ImageKit (Media Optimization & DAM) MCP Server gives your AI agent full control over your cloud media vault. List files, audit EXIF metadata, update asset tags, purge CDN caches, and delete assets—all through natural conversation.
This tool lets you manage the entire asset lifecycle without touching a console or leaving your IDE.
What your AI agents can do
Create custom schema
Creates a new custom metadata field or data structure for your assets.
Get exif metadata
Retrieves the structural data embedded in an image, like ISO, dimensions, and focal length.
Get file details
Gets explicit details about a specific file ID, including cloud logging information.
Retrieve detailed structural properties like ISO, dimensions, and focal length for any given file.
See a list of all uploaded media files and retrieve their associated metadata and tags.
Force the global CDN to invalidate specific URLs, ensuring users always see the latest version of an image.
Modify custom tags or metadata fields for assets, either for single files or entire groups.
Irreversibly delete individual files or run batch removals to free up cloud storage space.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
ImageKit MCP Server: 10 Tools for Media Asset Management
Manage file listings, retrieve structural metadata, and purge CDN caches for all your visual assets using your AI client.
019d75b8create custom schema
Creates a new custom metadata field or data structure for your assets.
019d75b8get exif metadata
Retrieves the structural data embedded in an image, like ISO, dimensions, and focal length.
019d75b8get file details
Gets explicit details about a specific file ID, including cloud logging information.
019d75b8get purge status
Checks the current status of a CDN cache purge request.
019d75b8list custom fields
Lists all the custom metadata fields currently attached to your account.
019d75b8list media files
Lists all uploaded media assets and their basic metadata in the ImageKit vault.
019d75b8patch file details
Updates specific metadata or tags on an existing file ID.
019d75b8purge cdn cache
Invalidates a specific URL across the global CDN edge nodes.
019d75b8wipe batch assets
Deletes multiple specified assets at once in a controlled batch operation.
019d75b8wipe media asset
Permanently deletes a single asset from the cloud storage.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with ImageKit (Media Optimization & DAM), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Listen up. This ImageKit MCP Server gives your AI agent total control over your cloud media vault. You'll manage every asset's lifecycle—listing files, checking metadata, updating tags, purging caches, and deleting assets—all through natural conversation. You won't need to touch a console or leave your IDE.
Audit Asset Metadata: You can use list_media_files to see every uploaded media asset and get its basic metadata and tags. If you need the deep structural specs—like ISO, dimensions, or focal length—you run get_exif_metadata on any file. You can also get explicit details about a specific file ID, including cloud logging info, using get_file_details.
You'll always know what you're working with.
Update Asset Data: Need to change tags or metadata? You can use patch_file_details to update specific metadata or tags on an existing file ID. If you need a whole new data structure, you'll run create_custom_schema to build a custom metadata field or data structure for your assets. You can check what custom fields are already attached with list_custom_fields.
Manage Storage Cleanup: To get rid of files, you've got two options: you can permanently delete a single asset with wipe_media_asset, or you can run wipe_batch_assets to delete multiple specified assets in one go. You'll free up your cloud storage space that way.
Purge CDN Cache: When you update an asset, you gotta make sure the public sees the fresh version. You run purge_cdn_cache to invalidate a specific URL across the global CDN edge nodes. You can also check the status of a purge request using get_purge_status to make sure it worked.
How ImageKit MCP Works
- 1 Subscribe to the server and enter your ImageKit Private Key.
- 2 Your AI client sends a natural language request (e.g., 'Purge the cache for X URL').
- 3 The server invokes the correct tool (like
purge_cdn_cache) and returns the status and result.
The bottom line is you manage your media vault by talking to your agent, not by clicking through a console.
Who Is ImageKit MCP For?
This is for the developer who needs to manage assets without leaving the IDE. It's for the content ops engineer tired of manually checking file properties across dozens of projects. If you're on a marketing team that needs to ensure every visual asset has correct SEO tags, this is for you.
Uses the agent to verify image delivery URLs and purge CDN cache right from their IDE after pushing asset updates.
Audits large media libraries, pulling structural image properties (like focal length or ISO) and organizing assets using natural conversation.
Automates asset lifecycle management, ensuring metadata is consistent and caches are always clean across development environments.
What Changes When You Connect
- Audit metadata and track assets. Use
get_exif_metadatato pull structural image data (focal length, ISO) andlist_media_filesto see everything in your vault. This saves you from opening image properties panels one by one. - Ensure fresh content delivery. After uploading or updating an asset, run
purge_cdn_cachewith the specific URL. Your agent handles the cache invalidation and tells you when it's done. - Keep your data clean. Don't let old files pile up. Use
wipe_batch_assetsto run bulk removals orwipe_media_assetto delete single files, optimizing your cloud storage space. - Maintain data structure. Use
create_custom_schemato define new metadata fields (e.g., 'Campaign Quarter'). Then, uselist_custom_fieldsto verify they exist, making your DAM consistent. - Patch assets on the fly. If you need to change a tag or update a description on a specific file,
patch_file_detailshandles it. No need to download, edit, and re-upload the file just to change a tag.
Real-World Use Cases
Updating a Campaign Hero Image
A marketing team member just swapped out the main hero banner. Instead of manually logging into ImageKit, finding the old URL, and waiting for the cache to clear, they tell their agent: 'Purge the cache for this URL.' The agent runs purge_cdn_cache, and the site instantly shows the new image.
Data Compliance Audit
The content ops team needs to verify every photo in the archive has a proper 'Project ID' tag. They use list_media_files to see the assets, then run list_custom_fields to check the existing schema, and finally use patch_file_details to apply the missing tag across hundreds of files.
Troubleshooting Broken Images
A developer sees an old version of an image on the live site. They ask their agent to run get_file_details on the URL path, which confirms the file ID, and then immediately runs get_purge_status to ensure the cache invalidation job is actually running.
Cleaning Up Stale Assets
The team finds old, unused product shots taking up gigabytes of storage. They use list_media_files to find the files, select the IDs, and run wipe_batch_assets to delete them irreversibly, keeping the storage costs down.
The Tradeoffs
Manually copying URLs
Trying to purge a cache by copying and pasting URLs one by one into the ImageKit console. This is slow, tedious, and you'll burn out before you're done.
→
Let your agent run purge_cdn_cache with the full list of URLs. You just give the list, and the tool handles the bulk invalidation. Check the status using get_purge_status after.
Assuming data integrity
Uploading a new asset and assuming its metadata is correct. If you don't check, you might miss critical EXIF data or required custom tags.
→
Always run get_exif_metadata immediately after uploading to verify the file's structural properties. You can also use patch_file_details to add required tags.
Overwriting data accidentally
Running a bulk operation without first checking what data exists. You might accidentally wipe out a schema or overwrite important tags.
→
Always run list_custom_fields first. This shows you exactly what custom fields are available before you attempt to create a new one with create_custom_schema.
When It Fits, When It Doesn't
Use this server if you manage media assets in a cloud environment and need to control the entire asset lifecycle—listing, metadata auditing, tagging, and purging—via conversational prompts. You need it if your workflow involves multiple, distinct steps: (1) Checking what exists (list_media_files), (2) Checking the file's inherent properties (get_exif_metadata), and (3) Updating or cleaning it (patch_file_details or wipe_media_asset).
Don't use this if you only need a simple file hosting service. If your need is just to store files without any metadata control or CDN management, a basic cloud storage bucket will work. If your workflow is complex but doesn't involve images (e.g., text documents), this server is overkill. You'll need a different kind of tool.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ImageKit. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking asset metadata and purging CDN caches shouldn't feel like a three-hour manual process.
Today, managing an asset means jumping between the ImageKit dashboard, the CDN status page, and your internal DAM system. You download the image, check the EXIF data in one tab, then copy the URL to the cache purge tool, and finally, go back to a spreadsheet to manually tag the metadata. It’s a mess of clicks and copy-pasting.
With this MCP server, you just talk to your agent. You ask it to 'List all assets and check the ISO and focal length for the top 10.' The agent runs `list_media_files` and `get_exif_metadata` for you, compiling the results instantly. You get the data, and you get it fast.
ImageKit MCP Server: Patching and Purging Assets
Previously, updating an asset's tags or purging its cache was a two-step nightmare. You'd have to manually update the tag in the console, and then separately go back to the CDN panel to invalidate the URL, hoping you got the right path. One step failed, and the image looked wrong anyway.
Now, you tell your agent, 'Update the 'Client Name' tag on this asset and purge the cache.' The agent runs `patch_file_details` and `purge_cdn_cache` in sequence, guaranteeing both steps happen. It’s a single command, and it works.
Common Questions About ImageKit MCP
How do I use `list_media_files` to find all my images? +
Running list_media_files gives you a clean list of all uploaded assets and their basic metadata. This is your starting point for any audit or cleanup job.
Is `purge_cdn_cache` the right way to update an image? +
Yes. If you change an image, you must run purge_cdn_cache on the specific URL. This forces the global CDN to fetch the newest version, ensuring no user sees an outdated image.
What is the difference between `wipe_media_asset` and `wipe_batch_assets`? +
wipe_media_asset deletes one file ID permanently. wipe_batch_assets is for deleting multiple files in a single, automated job.
Can I add custom data fields with `create_custom_schema`? +
Absolutely. create_custom_schema lets you define new metadata fields that match your business needs, extending the standard asset data structure.
How do I check if my cache purge actually worked? +
You run get_purge_status. This tool verifies the current status of the cache invalidation request and confirms the cleanup job is complete.
How does `get_exif_metadata` help me audit image quality? +
It retrieves structural details like ISO, focal length, and dimensions. You can use this to verify if assets meet specific quality standards before deployment.
What fields can I manage with `patch_file_details`? +
You can mutate existing properties, like updating tags or changing document schemas. This lets you maintain an organized, up-to-date digital asset library.
When should I use `list_custom_fields` instead of `list_media_files`? +
Use list_custom_fields to see what custom data fields are available for your project. list_media_files shows the actual visual assets you've uploaded.
Can I purge the CDN cache for a specific image using my agent? +
Yes. Use the purge_cdn_cache tool by providing the fully qualified delivery URL. Your agent will trigger the invalidation at the global Edge nodes and return a Request ID that you can use to track the status.
How do I see technical EXIF data for an uploaded file? +
The get_exif_metadata tool allows your agent to extract raw structural matching from an image, exposing technical details like focal length, ISO, and camera settings directly in your conversation.
Can I update tags for multiple images at once? +
While the patch_file_details tool focuses on individual files, your agent can process multiple files sequentially through natural language commands, making it easy to overwrite tags across your media vault.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
HTMLCSSToImage
Generate high-quality images and PDFs from HTML/CSS or URLs directly from your AI agent.
JokeAPI Alternative
Access thousands of jokes — audit categories and flags via AI.
Hyperbrowser (Web Infra for AI)
Cloud browsers for AI agents via Hyperbrowser — manage sessions, scrape pages, and extract structured data.
You might also like
TrueFoundry
Universal LLM Gateway & ML deployment hub: invoke 1000+ proxy models and manage MCP service instances natively.
Exa
Find exactly the web content you need with semantic search that understands context and returns high-quality curated results.
BrandMentions
Monitor social listening and brand mentions via BrandMentions — track keywords, manage projects, and list influencers directly from any AI agent.
