How to Use the Webiny CMS MCP in Claude Code

Q: How do I list all articles in Webiny CMS using Claude Code?

Use listmodelentries. Provide the plural model name, like 'Articles', and set the apitype to 'read' if you want live content or 'manage' for drafts. The output is a clean JSON list ready for scripting.

Q: What data type can I retrieve details for using Webiny CMS with Claude Code?

You use getmodelentrydetails and must provide the specific revision ID. This tool returns all field values associated with that unique content model entry, allowing your pipeline to process granular data.

Q: Can I programmatically create new drafts in Webiny CMS?

Yes, use createcmsentry. You only need to supply the single model name and a JSON object with field values. This automatically writes the entry into the system's draft queue for later review or publishing.

Q: If I run an experiment query on Webiny CMS, how do I execute it?

Execute executegraphqlquery. You define the desired API type (e.g., 'preview') and pass your raw GraphQL string. This is ideal for running read-only queries against a staging environment without affecting live data.

Q: Does this MCP Server handle global settings for Webiny CMS?

Yes, gettenantconfig pulls the global system variables for your entire content platform. This ensures that any automated job running in your CI/CD pipeline uses the current, correct set of tenant parameters.

Run Webiny CMS content workflows headlessly using Claude Code in CI/CD pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Webiny CMS MCP to Claude Code

Create your Vinkius account to connect Webiny CMS to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Webiny CMS with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Content Deployment for Webiny CMS

You can't manually click 'publish.' Use `publish_cms_entry` to make a draft live. In a CI/CD pipeline, you first need the revision ID via `list_model_entries`. Then, piping that ID into `publish_cms_entry` makes the content instantly available for testing or production builds. This allows reliable automated publishing: trigger the process, and the CMS entry moves from draft to 'read' status without human intervention.

Schema Validation via GraphQL with MCP Server

Before deploying a new feature, you must validate assumptions. Run `get_api_introspection` in your script. This retrieves the complete GraphQL schema, confirming that all field names and types used by your code are valid within Webiny CMS. This step is critical for stable pipelines, preventing runtime errors caused by forgotten API changes or model name mismatches.

Managing Content State Changes in CI/CD

Need to replicate a content change? You can use `update_cms_entry` and pass the entry ID and JSON payload. This simulates making a specific field update—like changing a featured image URL or correcting a typo—in your build script. It's perfect for testing rollback scenarios, allowing you to programmatically set an entry back to a known good state.

Setup guide

Set up Webiny CMS MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see webiny-cms-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Webiny CMS transactions." It will automatically discover and invoke the available Webiny CMS tools.

Terminal

claude mcp add --transport http webiny-cms-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Webiny CMS MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "webiny-cms-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Webiny. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Webiny CMS now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Webiny CMS MCP in Claude Code

Use `list_model_entries`. Provide the plural model name, like 'Articles', and set the `api_type` to 'read' if you want live content or 'manage' for drafts. The output is a clean JSON list ready for scripting.

You use `get_model_entry_details` and must provide the specific revision ID. This tool returns all field values associated with that unique content model entry, allowing your pipeline to process granular data.

Yes, use `create_cms_entry`. You only need to supply the single model name and a JSON object with field values. This automatically writes the entry into the system's draft queue for later review or publishing.

Execute `execute_graphql_query`. You define the desired API type (e.g., 'preview') and pass your raw GraphQL string. This is ideal for running read-only queries against a staging environment without affecting live data.

Yes, `get_tenant_config` pulls the global system variables for your entire content platform. This ensures that any automated job running in your CI/CD pipeline uses the current, correct set of tenant parameters.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript