How to Use the DatoCMS MCP in Mastra AI

Q: How do I make my Mastra AI agent ask for permission before deleting DatoCMS content?

When you define your agent, enable Mastra's requireToolApproval setting for the wipecmsrecord tool. Before the agent can execute the deletion, it will pause and wait for a human to approve the action.

Q: What's the difference between listcmarecords and executegraphqlcda?

listcmarecords is for getting raw data from the Content Management API, which is good for admin tasks. executegraphqlcda queries the read-only Content Delivery API, which is better for fetching content to display on a live site.

Build resilient content automation for DatoCMS with Mastra AI. Create multi-step workflows that publish, update, and clean up content without manual checks.

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 Mastra AI

Create your Vinkius account to connect DatoCMS to Mastra 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 DatoCMS with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Unbreakable Content Pipelines

Connect Mastra AI to your DatoCMS account through this MCP Server and build real content workflows. A common one: an agent watches for a new draft, runs a check, then publishes it by calling `patch_cms_record` to change its status. Mastra's engine handles retries if the API hiccups. You can chain operations together. For example, create a new record with `create_cms_record`, wait for an external check, and then update it with more details. If any step fails, Mastra can roll back the change or notify an admin.

Your DatoCMS Content Janitor

This is how you automate cleanup. Build a Mastra AI agent that periodically scans for old content with `list_cma_records` and archives or deletes it using `wipe_cms_record`. You set the rules, the agent does the work. It's perfect for media management, too. The agent can use `list_media_uploads` to find unattached images and then call `wipe_media_upload` to free up storage. With Mastra's `requireToolApproval`, you can add a human-in-the-loop step before any permanent deletion.

A Dependable Mastra AI Agent Connection

Your agent needs to know your content structure to work effectively. It can call `list_global_models` to get a current list of all your DatoCMS item types. This lets it build valid payloads for creating or updating records without guesswork. The connection is solid. Mastra AI automatically detects the best transport to the MCP server. Your agent just calls the tools it needs, like `get_single_record`, and the framework ensures the request gets through.

Setup guide

Set up DatoCMS MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All DatoCMS tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "datocms-mcp-client",
  servers: {
    "datocms-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "DatoCMS Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to DatoCMS tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent DatoCMS transactions"
);
console.log(result.text);

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 Mastra AI

Create a Mastra AI workflow triggered by a schedule. The agent would use `list_cma_records` to find posts with a 'ready to publish' status, then use `patch_cms_record` to make them live at the right time.

Yes, that's a great use case for this MCP connection. The agent can periodically call `list_media_uploads` and cross-reference the results with records from `list_cma_records` to find orphaned files. It then uses `wipe_media_upload` to remove them.

When you define your agent, enable Mastra's `requireToolApproval` setting for the `wipe_cms_record` tool. Before the agent can execute the deletion, it will pause and wait for a human to approve the action.

`list_cma_records` is for getting raw data from the Content Management API, which is good for admin tasks. `execute_graphql_cda` queries the read-only Content Delivery API, which is better for fetching content to display on a live site.

Your DatoCMS content models and record data are passed through Vinkius's secure sandbox only when a tool is active. Each request is isolated and ephemeral. The MCP server has no memory and doesn't retain any information about your content after the tool call is complete.

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