Crafter CMS MCP. Manage content, queries, and publishing workflows.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Crafter CMS MCP Server lets your AI agent manage your headless content lifecycle. Execute raw GraphQL queries, write XML content into Git, and trigger live publishing workflows—all without opening the Studio interface.
Use your agent to audit site configurations, trace complex content hierarchies, or search content across global sites.
What your AI agents can do
Execute graphql payload
Runs raw GraphQL queries against the Headless Crafter Engine to identify bounded data routing spaces.
Get site config
Retrieves explicit Cloud logging tracing specific Payload IDs and site limits.
Get site globals
Enumerates all attached structured rules and exports active site configuration variables.
Run raw GraphQL payloads to retrieve specific data points from the delivery schema.
Retrieve attached structured rules and site configuration details.
Trace the nested XML structure and properties driving the active Git content hierarchy.
Generate and provision XML payloads to create new content nodes or pages in the Git repository.
Trigger the automated workflow needed to move changes from the Studio environment to the live Delivery Engine.
Perform full-text queries across all content nodes using integrated Elasticsearch.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Crafter CMS MCP Server: 10 Tools for Content Ops
These tools let your agent interact with the CMS backend, allowing you to write content, audit site structures, run queries, and manage deployments programmatically.
019d757dexecute graphql payload
Runs raw GraphQL queries against the Headless Crafter Engine to identify bounded data routing spaces.
019d757dget site config
Retrieves explicit Cloud logging tracing specific Payload IDs and site limits.
019d757dget site globals
Enumerates all attached structured rules and exports active site configuration variables.
019d757dget studio tree
Performs structural extraction of properties and traces the nested XML structures in the Git hierarchy.
019d757dlist platform sites
Identifies and lists all active platform sites spanning different rented Context domains.
019d757dlist studio users
Retrieves structural data matching and verifies blueprint constraints for CMS users.
019d757dpublish crafter content
Executes workflow boundaries to migrate content changes from the Studio environment to the live Delivery Engine endpoint.
019d757dsearch crafter delivery
Inspects deep internal arrays to find content matching specific criteria across the delivery system.
019d757dwipe studio xml
Irreversibly deletes specified content nodes and drops live database bytes from the Studio XML.
019d757dwrite studio xml
Generates and provisions a highly-available XML payload to create new content nodes or pages.
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 Crafter CMS, 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
Crafter CMS MCP Server lets your AI agent manage your headless content lifecycle. You'll run raw GraphQL payloads against the Headless Crafter Engine to find specific, bounded data routing spaces. You can use get_site_config to check Cloud logging tracing specific Payload IDs and site limits, and get_site_globals enumerates all attached structured rules and exports active site configuration variables.
You'll use list_platform_sites to identify and list every active platform site across different rented Context domains. To audit user permissions, list_studio_users retrieves structural data matching and verifies blueprint constraints for CMS users. You can map the content structure and hierarchy using get_studio_tree, which performs structural extraction of properties and traces the nested XML structures in the Git hierarchy.
You'll find content using search_crafter_delivery, which inspects deep internal arrays to find content matching specific criteria across the delivery system. You'll generate and provision a highly-available XML payload to create new content nodes or pages using write_studio_xml. You can publish changes live by executing workflow boundaries with publish_crafter_content, moving content changes from the Studio environment to the live Delivery Engine endpoint.
You can also wipe content nodes and drop live database bytes from the Studio XML by running wipe_studio_xml.
How Crafter CMS MCP Works
- 1 Subscribe to the server and provide your Crafter CMS Base URL and Access Token (found in Crafter Studio > Token Management).
- 2 Instruct your AI client (Claude, Cursor, etc.) to perform a content action, like 'List all sites in my deployment' or 'Write a new XML page for the marketing site'.
- 3 The client uses the appropriate tool (e.g.,
list_platform_sitesorwrite_studio_xml) and sends the required payload; the server executes the action and returns the structured result.
The bottom line is, your agent talks to the CMS API directly, giving you command-line access to content publishing and structure management.
Who Is Crafter CMS MCP For?
This is for the Content Developer who needs to test GraphQL queries or write XML content nodes without opening the Studio UI. It's for the DevOps Engineer monitoring site configurations and verifying publication workflows across environments. And for the Technical Marketer needing to search content across global sites and audit metadata.
Tests GraphQL queries and writes raw XML content nodes directly from the agent to the Git repository.
Monitors site configurations, verifies publication workflows, and audits environment variables across different CMS environments.
Searches for specific content across global sites and audits content metadata using natural language prompts.
What Changes When You Connect
- Run complex queries without the UI. You can use
execute_graphql_payloadto test deeply nested data paths and validate schema requirements, moving testing from the browser console to your agent's chat. - Audit content structures safely. The
get_studio_treetool allows you to trace the exact nested XML properties driving your Git content hierarchy, something impossible to view easily in the main Studio view. - Control deployment from chat. Instead of clicking through a build process, you call
publish_crafter_contentto automatically trigger the migration of changes from Studio to the live Delivery Engine. - Find anything, anywhere. Use
search_crafter_deliveryto run full-text queries across all content nodes, making metadata searching as easy as asking your agent a question. - Manage content lifecycle programmatically. You can use
write_studio_xmlto generate and provision new XML payloads, letting your agent build entire pages or components based on a prompt. - Keep track of environments. Tools like
list_platform_sitesandget_site_configlet you list and verify site configurations across multiple domains, critical for multi-environment testing.
Real-World Use Cases
Site-wide Content Audit
The Technical Marketer needs to know if the 'Privacy Policy' exists on all 5 active client sites. They prompt their agent: 'List all platform sites, then check the metadata for 'Privacy Policy' on each.' The agent uses list_platform_sites first, then cycles through the results, using search_crafter_delivery to confirm the content's existence and status across every domain.
Creating a New Page Skeleton
The Content Developer needs a new landing page but doesn't want to open the Studio. They ask their agent to 'Create a basic XML structure for a product page for the 'Summer Sale' site.' The agent uses write_studio_xml to generate the required XML payload, which is then committed to the Git repository, giving the developer the starting point instantly.
Validating Deployment Readiness
The DevOps Engineer has updated the site's global variables and needs to verify the changes before deploying. They ask the agent to 'Check the current global variables and site configuration for the production environment.' The agent runs get_site_globals and get_site_config, confirming the required variables are present and structured correctly before initiating publish_crafter_content.
Rebuilding a Broken Section
The Content Developer notices a key section's XML structure is corrupt. They ask the agent to 'Show me the nested XML structure for the product line at /product/line-x.' The agent runs get_studio_tree to map the exact properties and nested folders, allowing the developer to pinpoint and fix the structural issue before rewriting the content.
The Tradeoffs
Blind GraphQL Execution
The developer runs execute_graphql_payload with a complex query without first checking the required site variables or environment status, causing the query to fail because it targets an unconfigured data path.
→
First, use get_site_config to verify the target site's GraphQL URL and payload IDs. Then, execute the query via execute_graphql_payload. This ensures the query runs against a known, valid data contract.
Over-reliance on the UI
Trying to track down a single piece of metadata or a structural variable by manually navigating the Crafter Studio UI, which involves dozens of clicks and context switching.
→
Use get_site_globals to enumerate all attached structured rules and pull the exact variable name and value into your agent's context. This instantly surfaces the data without touching the UI.
Uncontrolled Content Deletion
Deciding to 'delete' a large section of content by guessing the path and running a destructive command without confirming the scope, risking irreversible data loss.
→
Before deletion, run get_studio_tree to safely map the exact Git path and nested XML structure. This allows you to confirm you are only wiping the intended nodes before calling wipe_studio_xml.
When It Fits, When It Doesn't
Use this server if your workflow requires treating the CMS like a command-line tool—if you need to write XML, audit global variables, or run raw GraphQL payloads against the data schema. You need programmatic control over the content lifecycle. Don't use this if you just need to view content or read simple text; for that, a standard content search tool is enough. If you are only checking connectivity, use list_platform_sites first. If you are modifying content, always check the environment using get_site_config before using write_studio_xml or publish_crafter_content to prevent deploying changes to the wrong site.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crafter 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 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually auditing content structure is a nightmare.
Right now, checking if a piece of content follows the right structure—like knowing exactly which fields or nested XML nodes are active—requires deep diving into the Studio's structural tree, often involving multiple manual checks and copy-pasting paths.
With the Crafter CMS MCP Server, you simply ask your agent to map the structure. Using `get_studio_tree` gives you a complete, auditable trace of the Git hierarchy and all required XML properties. You get the map, instantly.
Write content and publish changes with Crafter CMS MCP Server
Before this, generating a new page meant manually creating the content, then updating the site variables, and finally clicking 'Publish' in a specific order. If you missed one step, the content broke or failed to deploy.
Now, your agent handles the whole sequence. You can tell it to 'Write the new page and deploy it.' The server uses `write_studio_xml` and then triggers `publish_crafter_content`, ensuring the content is created and validated live in one go.
Common Questions About Crafter CMS MCP
How do I find all the sites I have deployed in Crafter CMS using list_platform_sites? +
The list_platform_sites tool returns a list of all active sites and their unique IDs. This is useful for confirming which domains are connected to the CMS and determining the scope of your content operations.
Can I run a custom query on a specific site using execute_graphql_payload? +
Yes. You run the raw GraphQL payload through execute_graphql_payload, specifying the target site and the exact query structure. This allows you to test complex data requirements that standard search tools can't handle.
What is the difference between get_site_config and get_site_globals? +
They serve different purposes. get_site_config retrieves the site's technical configuration and logging payload IDs. get_site_globals enumerates the custom, structured variables attached to the site, like unique site names or API keys.
How do I create a new page or component using write_studio_xml? +
Use write_studio_xml by providing the necessary XML payload and defining the content nodes. This tool provisions the content and makes it available in the Git repository for review.
Does publishing content via publish_crafter_content automatically validate it? +
Yes. The tool triggers an automated validation check, migrating the changes from the Studio environment to the high-performance Delivery Engine, confirming the deployment status.
How do I check the content structure for a specific path using get_studio_tree? +
The get_studio_tree tool traces nested XML structures safely. It returns a map of all properties and folders within a specified Git hierarchy, allowing you to see the exact content structure before you write anything.
What information does `get_site_globals` expose about a site's configuration? +
get_site_globals enumerates explicitly attached structured rules. It retrieves active site configuration variables, such as global API keys or required front-end SDK variables, that apply across the whole site.
How do I search content across all sites using search_crafter_delivery? +
The search_crafter_delivery tool inspects deep internal arrays. You provide a search query and the tool performs full-text searching across all content nodes and metadata across your entire Crafter delivery platform.
Can my agent write new content files to Crafter Studio via Git? +
Yes. Use the 'write_studio_xml' tool. Provide the site name, file path, and raw XML content. The agent will command the backend to write the physical Git boundaries, generating new content nodes or pages directly in your Studio environment.
How do I publish changes from Studio to the live Delivery Engine? +
Use the 'publish_crafter_content' tool. Provide the site name and the specific object path. Your agent will trigger the automated publication workflow, migrating the changes from your Git-based Studio repo to the live high-performance delivery endpoint.
Can I perform full-text searches across all site content? +
Absolutely. The 'search_crafter_delivery' tool leverages Crafter's Elasticsearch integration. Your agent can pull explicitly queried words spanning all nodes, returning matches based on the query logic defined in your search engine.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
IP Subnet Calculator
Flawless binary math. Calculate perfect network boundaries, broadcast addresses, and IP ranges without LLM hallucination.
Neptune.ai (ML Experiment Tracking)
Manage ML experiments via Neptune.ai — track training runs, monitor metrics, and audit model versions.
Markdown HTML Compiler
Stop wasting AI tokens converting text. Compile Markdown into clean, minified HTML instantly for emails and CMS platforms.
You might also like
PlanetScale
Provision, branch, and manage serverless MySQL databases dynamically via AI.
Agile CRM
Manage contacts, deals, and marketing campaigns in one place with a CRM built for growing sales teams.
RocketReach
Find accurate contact information for professionals and companies with a database of verified emails and direct phone numbers.