How to Use the Webiny CMS MCP in AutoGen

Q: How does Webiny CMS and AutoGen handle content creation?

Agents use createcmsentry to draft the initial record. The multi-agent debate then refines this JSON payload before it's committed as a new entry revision.

Q: Can I test publishing logic with Webiny CMS and AutoGen?

Yes. You can have agents compare content from listmodelentries against the requirements for publishcmsentry, ensuring that only fully vetted drafts are ever published.

Q: Does Webiny CMS support multi-locale workflows with AutoGen?

Absolutely. The executegraphqlquery tool requires a locale parameter, allowing competing agents to debate and manage content across multiple language versions simultaneously.

Q: How do I retrieve specific entry details using Webiny CMS and AutoGen?

The agents use getmodelentrydetails to pull granular information tied to a specific revision ID. This detail is then fed back into the debate for final consensus.

Force consensus decisions on Webiny CMS with AutoGen.

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 AutoGen

Create your Vinkius account to connect Webiny CMS to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate Content Changes

The `update_cms_entry` tool allows multiple agents to debate field changes for an existing entry. For instance, a 'Security Agent' might flag risk in the content, while a 'Performance Agent' suggests shortening copy. They can then converge on a single, agreed-upon JSON object to pass back.

Evaluate Draft Readiness

Agents use `list_model_entries` to assess the readiness of content models. One agent might check if all required fields are present, while another calls `get_tenant_config` for publishing rules. This debate process ensures the final decision—to publish or not—is consensus-driven.

Simulate Publishing Workflows

The system can model the publication process. One agent drafts content using `create_cms_entry`, and another debates whether it should be published by calling `publish_cms_entry` only when all checks pass. This gives you a repeatable, verifiable workflow for complex CMS tasks.

Setup guide

Set up Webiny CMS MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Webiny CMS tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Webiny CMS_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Webiny CMS data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Webiny CMS_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Webiny CMS data")
    print(result.messages[-1].content)

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 AutoGen

Agents use `create_cms_entry` to draft the initial record. The multi-agent debate then refines this JSON payload before it's committed as a new entry revision.

Yes. You can have agents compare content from `list_model_entries` against the requirements for `publish_cms_entry`, ensuring that only fully vetted drafts are ever published.

Absolutely. The `execute_graphql_query` tool requires a locale parameter, allowing competing agents to debate and manage content across multiple language versions simultaneously.

The 'Safety Agent' can be tasked with reviewing the necessity of `delete_cms_entry`. Since this action is permanent, having a debate over its risk mitigates accidental data loss.

The agents use `get_model_entry_details` to pull granular information tied to a specific revision ID. This detail is then fed back into the debate for final consensus.

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