How do I connect my Webiny instance?

You just need to provide your Webiny API Domain and your Access Token during the setup process in Vinkius.

Which AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I run custom GraphQL queries?

Yes, the execute_graphql_query capability allows you to run raw queries or mutations against your API.

Does this support multiple languages?

Yes, you can manage content across different locales using the multi-locale support built into the capabilities.

Is deleting an entry permanent?

Yes, the delete_cms_entry capability performs an irreversible action that removes the content revision.

Can I publish a draft content entry via chat?

Yes. The publish_cms_entry capability allows you to take any draft revision live. You just need to provide the entry ID and the model name, and your AI agent will handle the publication through the Webiny 'manage' API.

Is it possible to see the entire GraphQL schema of my instance?

Absolutely. Using the get_api_introspection capability, your agent can retrieve the full GraphQL schema introspection, giving you a complete overview of all available types, fields, and content models in your environment.

How do I add a new entry to a content model through conversation?

Use the create_cms_entry capability. Provide the singular model name (e.g., 'Article'), the target locale, and a JSON object containing the field data. Your agent will create the new draft entry instantly.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Webiny CMS to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run your entire content operations through a chat interface.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through Webiny.

01
Create cms entry
This capability creates a new draft entry for a specific content model. You just need to provide the model name and the field data as a JSON object.
02
Delete cms entry
This capability permanently removes a content entry revision. Use this with caution as the action cannot be undone.
03
Get API introspection
This capability pulls the GraphQL schema introspection for your Webiny instance. It helps your agent understand your available types and fields.

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through Webiny.

04
List model entries
This capability retrieves all entries for a specific content model. You can specify if you want to see drafts via the manage API or live content via the read API.
05
Update cms entry
This capability modifies the fields of an existing content entry revision. You provide the entry ID and the specific field updates in a JSON object.
06
Execute graphql query
This capability runs raw GraphQL queries or mutations against your Webiny API. You can define the api_type and the specific locale for the operation.

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through Webiny.

07
Get model entry details
This capability fetches the full details for a specific content model entry revision using its ID.
08
Get tenant config
This capability retrieves the global settings for your Webiny tenant. It is useful for checking your environment configuration.
09
Publish cms entry
This capability makes a draft entry live by publishing a specific revision ID. Once published, the content becomes available through the read API.

Real work

What teams actually run

Rapid Content Updates

Update specific fields in a content entry by simply describing the change to your agent.

Schema Debugging

Use introspection capabilities to quickly see if a new field was added to your content model.

Bulk Content Audits

List all entries for a specific model to verify that all required content is present and correctly localized.

Automated Publishing

Move drafts to live status by providing a revision ID to your agent.

Automate a task

Put Webiny to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Webiny works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Webiny to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

940ms average. Fast in production.

Webiny is checked daily against the live service.

Daily averagePeak 1160ms

Oct 3Today

Fastest day: 770ms
Slowest day: 1160ms
14-day trend: Slowing+26%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Webiny, so you can see the experience inside your AI.

It does not authenticate your account with Webiny. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Webiny Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_IUcCLFWKptm8T3ZnOC6XFGqdSwKmbpaEOYRidrry/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Webiny capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "webiny-cms-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_IUcCLFWKptm8T3ZnOC6XFGqdSwKmbpaEOYRidrry/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Webiny in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Webiny owners hand off.

This MCP is built for teams working with headless architectures who want to bypass manual API interactions.

01
Content Managers
They use the agent to update and publish entries across multiple models and locales without manual data entry.
02
Headless Developers
They use the agent to test GraphQL queries and verify content model structures through chat.
03
Marketing Teams
They use the agent to browse content items and check the publication status of various campaigns.
04
CMS Administrators
They use the agent to monitor tenant settings and audit content revisions using simple commands.

FAQ

Questions Webiny owners ask.

01
How do I connect my Webiny instance?
You just need to provide your Webiny API Domain and your Access Token during the setup process in Vinkius.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can I run custom GraphQL queries?
Yes, the execute_graphql_query capability allows you to run raw queries or mutations against your API.
04
Does this support multiple languages?
Yes, you can manage content across different locales using the multi-locale support built into the capabilities.
05
Is deleting an entry permanent?
Yes, the delete_cms_entry capability performs an irreversible action that removes the content revision.
06
Can I publish a draft content entry via chat?
Yes. The publish_cms_entry capability allows you to take any draft revision live. You just need to provide the entry ID and the model name, and your AI agent will handle the publication through the Webiny 'manage' API.
07
Is it possible to see the entire GraphQL schema of my instance?
Absolutely. Using the get_api_introspection capability, your agent can retrieve the full GraphQL schema introspection, giving you a complete overview of all available types, fields, and content models in your environment.
08
How do I add a new entry to a content model through conversation?
Use the create_cms_entry capability. Provide the singular model name (e.g., 'Article'), the target locale, and a JSON object containing the field data. Your agent will create the new draft entry instantly.

Explore

More in Developer Tools

Connect Webiny to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Create cms entry

Delete cms entry

Get API introspection

04-06

List model entries

Update cms entry

Execute graphql query

07-09

Get model entry details

Get tenant config

Publish cms entry

What teams actually run

Rapid Content Updates

Schema Debugging

Bulk Content Audits

Automated Publishing

Building your own app? The connector is yours to use.

Webiny Connector

Claude Desktop

Content Managers

Headless Developers

Marketing Teams

CMS Administrators

How do I connect my Webiny instance?

Which AI clients can I use with this MCP?

Can I run custom GraphQL queries?

Does this support multiple languages?

Is deleting an entry permanent?

Can I publish a draft content entry via chat?

Is it possible to see the entire GraphQL schema of my instance?

How do I add a new entry to a content model through conversation?

Joomla (Open-Source CMS) AI Connector

Contentful AI Connector

Data.gov Catalog AI Connector

Data Pipeline Prover AI Connector

Suggestions

Open Data Euskadi AI Connector

Amsterdam Open Data Explorer AI Connector

EU Open Data Portal AI Connector

Milvus (Open-Source Vector Database) AI Connector