How to Use the DatoCMS MCP in AutoGen

Q: How do I pass DatoCMS tools to AutoGen agents?

Use mcpservertools with your Vinkius endpoint URL. The adapter handles all schema conversions before you pass the list to your AssistantAgent.

Q: Can AutoGen agents delete DatoCMS records?

Yes, if you grant them access to wipecmsrecord. We recommend requiring human-in-the-loop approval before letting agents vaporize live document rows.

Give your AutoGen agents control over DatoCMS. Let multiple AI roles debate content edits before pushing them live.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DatoCMS MCP to AutoGen

Create your Vinkius account to connect DatoCMS 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 DatoCMS with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Content Debates via MCP

You don't want a single script publishing directly to your site. An editor agent drafts a post, but a compliance agent reviews it. They argue over the tone and structure before anything touches the DatoCMS database. Once they reach consensus, the execution agent takes over. It fires `create_cms_record` to inject the agreed-upon JSON payload into your headless architecture via this MCP Server.

Schema Negotiation and Updates

Changing a live website requires caution. A developer agent wants to alter a field, so it runs `list_global_models` to check the current structure. A QA agent steps in to warn about breaking changes. They review the active node details using `get_single_record`. Only after both agents agree that the mutation is safe will they authorize a call to `patch_cms_record`.

Automated Media Cleanup

Storage costs get out of hand quickly. You assign an audit agent to run `list_media_uploads` and identify unused files. A second agent verifies these files aren't linked anywhere in the active GraphQL tree via `execute_graphql_cda`. If the second agent confirms the file is orphaned, it approves the deletion. The first agent then executes `wipe_media_upload` to drop the asset from your cloud storage.

Setup guide

Set up DatoCMS 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 DatoCMS 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="DatoCMS_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DatoCMS 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="DatoCMS_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DatoCMS 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 DatoCMS. 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 DatoCMS 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 DatoCMS MCP in AutoGen

Use `mcp_server_tools` with your Vinkius endpoint URL. The adapter handles all schema conversions before you pass the list to your AssistantAgent.

Yes, if you grant them access to `wipe_cms_record`. We recommend requiring human-in-the-loop approval before letting agents vaporize live document rows.

Tools are stateless. Each agent calls the MCP Server independently, so a retrieval agent and a publishing agent can work in parallel.

One agent writes the query and another validates its syntax. They loop until the code is correct, then execute it via `execute_graphql_cda`.

Vinkius isolates your MCP server in a dedicated V8 sandbox. Your JSON payloads and media metadata never leak across tenants and vanish after the tool call completes.

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