Cockpit CMS MCP. Manage content, assets, and menus via natural conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Cockpit (Self-hosted Headless CMS API) MCP Server gives your AI agent full read/write control over your self-hosted CMS. Use it to list, create, update, and delete content collections, manage assets, and pull localized content data.
It lets your agent interact with your CMS structure via natural conversation, treating it like a native API call.
What your AI agents can do
Batch content items
Gets content from multiple collections in one API call.
Create or update content item
Makes a content item, or updates an existing one if you provide its ID.
Delete content item
Removes a content item using its unique ID.
List, retrieve, create, update, and delete content items across any collection using Mongo-style filters and IDs.
Fetch metadata for assets and generate resized images or thumbnails on demand.
Retrieve translations and localized project data from integrated localization services.
Get the sitemap, list all pages, or fetch specific menus and routes by name or path.
Fetch related content items from multiple collections in a single, high-performance request.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Cockpit CMS API: 17 Tools for Content & Asset Management
Use these tools to manage everything in your CMS—from content collections to localized assets—all through your AI agent.
019e5d09batch content items
Gets content from multiple collections in one API call.
019e5d09create or update content item
Makes a content item, or updates an existing one if you provide its ID.
019e5d09delete content item
Removes a content item using its unique ID.
019e5d09get asset
Retrieves the metadata for a specific asset ID.
019e5d09get asset image
Generates thumbnails or resized versions of an image.
019e5d09get content item
Fetches a single content item using its ID.
019e5d09get lokalize project
Gets all available translations for a specified Lokalize project.
019e5d09get lokalize project locale
Gets translations for a single language within a Lokalize project.
019e5d09get menu
Fetches a specific navigation menu by its name.
019e5d09get page by route
Retrieves a page's content using its URL route.
019e5d09get sitemap
Gets the complete, current sitemap for the site.
019e5d09list content items
Gets a list of items from a content collection, supporting filters and pagination.
019e5d09list menus
Lists every menu available in the CMS.
019e5d09list pages
Lists all defined pages in the CMS.
019e5d09list routes
Gets a lightweight list of all possible site routes and slugs.
019e5d09search detektivo
Searches for content within a specific Detektivo index.
019e5d09submit inbox
Submits form data to a designated Inbox for review.
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 Cockpit (Self-hosted Headless CMS API), 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
You're hooking up your self-hosted Cockpit CMS to your AI agent, giving it full read/write control over your whole content setup. This server lets your agent interact with your CMS structure using natural conversation, treating it just like a native API call. list_content_items gets you a list of items from any content collection, letting you filter and page through results. get_content_item pulls a single content item when you know its ID. create_or_update_content_item makes a new content item, or it updates one if you hand it an ID. delete_content_item removes a content item using its unique ID. batch_content_items pulls content from multiple collections in one call.
Need to deal with media? get_asset fetches metadata for a specific asset ID, and get_asset_image generates thumbnails or resized versions of an image when you need it.
Working with multiple languages? get_lokalize_project gets all available translations for a Lokalize project, and get_lokalize_project_locale fetches translations for a single language within that project.
Want to know what pages you've got? list_pages lists all defined pages, list_menus lists every menu in the CMS, and list_routes gives you a light list of all possible site routes and slugs. You can also get_menu to fetch a specific navigation menu by name. get_page_by_route retrieves a page's content using its URL route. get_sitemap grabs the complete, current sitemap for the site.
Got form data? submit_inbox submits form data to a designated Inbox for review.
search_detektivo searches for content within a specific Detektivo index.
How Cockpit CMS MCP Works
- 1 First, subscribe to the server and provide your Cockpit Instance URL and API Key.
- 2 Second, your AI agent connects to the server and sees the full list of available tools (e.g.,
list_content_items,get_asset). - 3 Third, you instruct your agent to perform a task—like 'Create a new blog post'—and it executes the required API calls to complete the workflow.
The bottom line is: you manage your CMS content and assets through natural language prompts, not through the CMS dashboard.
Who Is Cockpit CMS MCP For?
This is for Content Managers, Developers, and Marketing Leads who are tired of context-switching. If you spend more time clicking through dashboards, copy-pasting data, or manually checking asset dimensions than actually creating content, this server is for you. It puts your entire CMS backend directly into your AI agent's conversational flow.
Updates blog posts, changes product descriptions, or adds FAQs without ever logging into the CMS dashboard.
Queries content structures and asset metadata directly from their IDE while writing code, ensuring the front-end matches the CMS schema.
Quickly retrieves localized content and asset data for multi-channel campaigns across different languages.
What Changes When You Connect
- Update content instantly. Need to change a product description? Use
create_or_update_content_itemto modify the item directly, without opening the CMS dashboard. - Handle media on demand. Use
get_asset_imageto generate resized images and thumbnails for your campaigns. You get the exact dimensions you need, instantly. - Improve site structure visibility. Use
get_sitemapto get the complete sitemap in one call, allowing your agent to map out the entire site architecture. - Streamline global content. Use
get_lokalize_project_localeto pull specific language translations. This lets your agent manage multi-language content for global sites. - Boost performance with batching. Use
batch_content_itemsto fetch data from five different collections in a single request, keeping your agent's workflow fast. - Know your pages. Use
list_pagesorget_page_by_routeto quickly list all pages or fetch a page's content by its URL path.
Real-World Use Cases
Fixing a typo on a featured product page
The Marketing Manager spots a typo on the main product page. Instead of logging into Cockpit CMS, they tell their agent: 'Update the featured text in 'products' with ID 98765 to say 'Revolutionary'.'. The agent runs create_or_update_content_item and fixes it in seconds.
Building a multi-language blog index
The Global Editor needs the latest content for the French market. They ask their agent to get the translations using get_lokalize_project_locale for 'fr'. Then, they use batch_content_items to gather the necessary content from the 'blog' and 'products' collections.
Developer checking asset requirements
A developer needs to know the dimensions of a hero image before coding the layout. They ask the agent to use get_asset with the image ID. The agent returns the metadata, telling the developer if they need to run get_asset_image for a specific size.
Deprecating an old page
A content architect decides a page is obsolete. They tell the agent to use delete_content_item on the specific item ID. The agent executes the deletion, updating the CMS structure instantly.
The Tradeoffs
Sequential API Calls
Manually listing pages using list_pages, then calling get_page_by_route for each one, and finally running get_content_item for every piece of data. This is slow and fails if one endpoint times out.
→
Use get_sitemap first. Then, tell your agent to gather all necessary content by passing the list of routes to a single query. This approach is far faster and more reliable than chaining individual lookups.
Ignoring Localized Data
Assuming all content is stored in one place. A developer fetches content via get_content_item but forgets to account for the localized version, resulting in English content appearing on the Spanish site.
→
Always use get_lokalize_project_locale when building multi-market features. This tool ensures your agent pulls the correct language version for the intended market.
Over-relying on Listing Tools
Using list_content_items to find an item, then trying to read the item's content. If the list query is too broad, the agent might return hundreds of results, and you have to sift through them.
→
Always narrow the search. Use get_content_item with the exact ID, or use list_content_items with specific filters (e.g., status: draft and collection: blog). Don't rely on the list view for specific data.
When It Fits, When It Doesn't
Use this server if your workflow requires interacting with a self-hosted Cockpit CMS via natural language, and you need full CRUD control over content, assets, and menus. It's ideal for developers who want to query schema or update content directly from an IDE, or for content teams who want to automate publishing workflows.
Don't use this if you only need to read basic sitemaps or list routes. In those cases, simpler, read-only APIs might suffice. Also, if your CMS is hosted on a different platform, this server won't work. The power here is the direct, conversational control over your specific Cockpit instance.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cockpit CMS. 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 17 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Managing Content Means Logging In and Clicking Through Dashboards
Right now, updating a single piece of content—say, changing the text on a product page—requires logging into the CMS, navigating to the correct collection, finding the item, clicking edit, making the change, and hitting save. This process is slow, prone to human error, and forces you to context-switch away from your primary work.
With this MCP server, you just tell your agent: 'Update the product description for ID 98765 to mention the new battery life.' The agent runs the `create_or_update_content_item` tool, and the change is live. You get the result without leaving your chat interface.
Cockpit CMS API MCP Server: Content & Asset Operations
The ability to fetch metadata for an asset using `get_asset` means you don't have to manually download and check the dimensions of a file. You ask the agent, and it tells you the size and format instantly. You also get to run `get_asset_image` to generate specific sizes for different channels.
This isn't just fetching data. It's giving your AI client the necessary plumbing to perform complex operations—from retrieving localized data via `get_lokalize_project_locale` to managing entire site structures with `get_sitemap`. It's a single, powerful layer of control.
Common Questions About Cockpit CMS MCP
How do I update a content item using the `create_or_update_content_item` tool? +
You must provide the item's unique ID, the content collection name, and the specific fields you want to change. The tool handles both creation and updates based on whether or not you supply an existing ID.
Can I get all translations for a project using `get_lokalize_project`? +
Yes, get_lokalize_project pulls a list of all available translations for the project. If you need content for a specific language, you run get_lokalize_project_locale and provide the locale code.
What is the best way to get a list of all content collections? +
The server doesn't have a single 'list collections' tool. You should use list_content_items and specify the collection name in your request filters to narrow down your search.
Does `get_sitemap` only give me URLs? +
No, get_sitemap provides the complete sitemap, which includes more than just URLs. It gives a full picture of the site's structure, helping your agent map the entire content graph.
How do I use `list_content_items` to filter and sort content collections? +
You can filter and sort by passing specific query parameters. For example, you can limit results by date range or sort by popularity. This makes fetching data precise and fast.
What should I do if I get an error when using `get_asset`? +
Check the provided asset ID first. If the ID is wrong, the tool returns a specific error code. You can then use get_asset_metadata to verify the asset's existence and correct the query.
Can I use `batch_content_items` to pull data from multiple content types at once? +
Yes, batch_content_items accepts an array of content model names. This lets your agent gather data from different collections (like 'blog' and 'products') in a single, efficient call.
Does `get_page_by_route` handle localized content retrieval? +
It retrieves the full content for a specific page route, regardless of locale. You still need to use get_lokalize_project_locale if you want to check the translation for a specific language.
Can I filter content items using Mongo-style queries? +
Yes! The list_content_items tool supports a filter parameter where you can pass a JSON object with Mongo-style query operators to precisely target your data.
Is it possible to resize images directly through the agent? +
Absolutely. Use the get_asset_image tool with parameters like w (width), h (height), and m (mode) to request processed versions of your stored image assets.
Can I fetch data from multiple collections at once? +
Yes, the batch_content_items tool allows you to define multiple models and their respective query parameters in a single JSON object to retrieve all required data in one go.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Bugcrowd
Manage crowdsourced security via Bugcrowd — track submissions, programs, and targets directly from any AI agent.
Blockchair (Universal Blockchain Search Engine & API)
Query blocks, transactions, and addresses across multiple blockchains like Bitcoin and Ethereum using Blockchair's universal API.
Lorem Picsum
Generate placeholder images and retrieve image metadata directly from your AI agent using the Lorem Picsum API.
You might also like
HelpCrunch
Engage customers with live chat, email automation, and a knowledge base that reduces support workload and boosts satisfaction.
Guestmeter
Automate guest feedback collection and reputation management via Guestmeter directly from any AI agent.
Capsule CRM
Manage your CRM via Capsule — track contacts, opportunities, and tasks directly from any AI agent.