How to Use the Webiny CMS MCP in Pydantic AI

Q: How do I list models safely using Webiny CMS and Pydantic AI?

Use listmodelentries. Because of the Pydantic validation, you'll get a predictable structure. You just need to provide the model plural name and specify if you want drafts or live content.

Q: What is the best way to read raw data in Webiny CMS using Pydantic AI?

Use executegraphqlquery. The agent can run any query or mutation, specifying the API type and locale. This gives you granular control over the exact data structure you are querying.

Q: How do I ensure my CMS workflow is correct using Webiny CMS and Pydantic AI?

You can check the schema first by calling getapiintrospection. This tool retrieves the entire GraphQL introspection, letting your agent validate all potential operations before running them.

Q: If I want to change content, what's the process in Webiny CMS using Pydantic AI?

You first get the details via getmodelentrydetails for a specific revision ID. Then, you use updatecmsentry, supplying the entry ID and your field updates.

Write reliable agents for Webiny CMS using Pydantic AI's type-safe data validation layer.

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 Pydantic AI

Create your Vinkius account to connect Webiny CMS to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Content Drafting and Modification

Start by calling `create_cms_entry` to draft a new piece of content. You pass the required model name and field data as a JSON object, which is then type-checked before being saved. If you need to change something later, use `update_cms_entry`. The agent provides the entry ID and the updated fields in a structured JSON format.

Comprehensive Model Listing

`list_model_entries` lets your agent list all entries for any model. It takes the plural name and an `api_type` (manage or read) to ensure the data returned is exactly what you need. For viewing global system settings, use `get_tenant_config`. This tool fetches the overall configuration data for the Webiny tenant.

Advanced Content Lifecycle Management

`publish_cms_entry` publishes a draft by requiring a specific revision ID. Once published, that content is available through the 'read' API. You can also perform deletions using `delete_cms_entry`. Remember, this function permanently removes a content entry revision and it cannot be undone.

Setup guide

Set up Webiny CMS MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "webiny-cms-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Webiny CMS tools.",
)

result = await agent.run("List recent Webiny CMS transactions")
print(result.output)

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 Pydantic AI

Use `list_model_entries`. Because of the Pydantic validation, you'll get a predictable structure. You just need to provide the model plural name and specify if you want drafts or live content.

Use `execute_graphql_query`. The agent can run any query or mutation, specifying the API type and locale. This gives you granular control over the exact data structure you are querying.

You can check the schema first by calling `get_api_introspection`. This tool retrieves the entire GraphQL introspection, letting your agent validate all potential operations before running them.

You first get the details via `get_model_entry_details` for a specific revision ID. Then, you use `update_cms_entry`, supplying the entry ID and your field updates.

This server handles Content Model Field Data. It allows the agent to manage drafts, publish live content, retrieve configuration settings, and execute complex GraphQL queries on that data.

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