How to Use the DatoCMS MCP in OpenAI Agents SDK

Q: How do I connect the DatoCMS MCP Server to OpenAI Agents SDK?

Pass the Vinkius URL to MCPServerStreamableHttp inside an async context manager. The SDK auto-discovers the tools. Set cacheToolsList=True to cut down initialization time on cold starts.

Q: Can my OpenAI Agents SDK system run custom GraphQL queries against DatoCMS?

Yes, the agent calls executegraphqlcda with your raw query string. It receives the exact JSON response from the Content Delivery API. You define the query structure, and the agent handles the transport.

Q: How do I handle rate limits when fetching multiple records?

Use listcmarecords to pull paginated JSON:API arrays in a single request. The SDK's built-in tracing shows exactly how many API calls your agent makes. You adjust the pagination limits based on those metrics.

Build production-ready headless content pipelines with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect DatoCMS to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

GraphQL execution via the DatoCMS MCP Server.

Your OpenAI Agents SDK setup dictates GraphQL execution via the DatoCMS MCP Server. The `execute_graphql_cda` tool routes queries directly into your headless tree. You get exact node data back without writing custom fetchers. Tracing happens automatically in your OpenAI dashboard. When your handoff agent pulls specific properties using `get_single_record`, you see the exact payload and latency metrics. This prevents bad queries from silently eating tokens.

Strict boundaries for content models.

Managing content models requires strict boundaries. The `list_global_models` tool enumerates the structured rules attached to your item types. Your safety-constrained agents read these definitions before attempting any writes. Write operations run through `create_cms_record` and `patch_cms_record`. Because the SDK validates actions before execution, your system blocks malformed JSON payloads before they ever hit the production CMS. You build content pipelines that actually respect schema rules.

Automated media auditing and removal.

Media handling stops being a manual chore. Your agent inspects internal storage arrays using `list_media_uploads` to find specific image blocks. It extracts structural matches through `get_media_upload`. Removals are explicit and tracked. Triggering `wipe_media_upload` drops the file from disk, while `wipe_cms_record` vaporizes the document row. The SDK guardrails ensure these destructive actions require explicit user confirmation before the agent fires the request.

Setup guide

Set up DatoCMS MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DatoCMS tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DatoCMS tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DatoCMS tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DatoCMS Agent",
            instructions="You have access to DatoCMS tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Pass the Vinkius URL to `MCPServerStreamableHttp` inside an async context manager. The SDK auto-discovers the tools. Set `cacheToolsList=True` to cut down initialization time on cold starts.

Yes, the agent calls `execute_graphql_cda` with your raw query string. It receives the exact JSON response from the Content Delivery API. You define the query structure, and the agent handles the transport.

You build specialized agents for different domains. A media agent uses `get_media_upload`, while a copywriter agent calls `patch_cms_record`. The framework passes context between them natively.

Use `list_cma_records` to pull paginated JSON:API arrays in a single request. The SDK's built-in tracing shows exactly how many API calls your agent makes. You adjust the pagination limits based on those metrics.

Your content schemas, GraphQL responses, and media URLs stay inside the Vinkius V8 Isolate Sandbox. The ephemeral container processes the JSON payloads and destroys itself after the run. We store zero persistent data from your CMS.

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