How to Use the Directus MCP in Mastra AI

Q: How do I handle a failed Directus database update inside a Mastra AI workflow?

Configure your agent to catch errors from patchcmsrecord or createcmsrecord. Mastra AI automatically retries the tool execution using its built-in exponential backoff mechanism.

Q: Can I require human approval before Mastra AI deletes a Directus record?

Yes, set the requireToolApproval flag on the wipecmsrecord tool schema. Mastra AI pauses the workflow and waits for your manual confirmation before dropping the row.

Q: How do I feed Directus collection schemas into Mastra AI agents?

Call getcollectiondetails inside your workflow's initialization step. Mastra AI parses the returned properties to construct valid JSON payloads for subsequent database writes.

Q: How do I find specific rows in a massive table using this MCP Server?

Run listcollectionitems to search bounded routing spaces inside your SQL mappers. This filters your dataset and returns only the relevant records to your agent.

Build resilient, self-healing database workflows in Mastra AI using your Directus schema.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Directus MCP to Mastra AI

Create your Vinkius account to connect Directus 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 Directus with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Directus schema mapping in Mastra AI

`list_schema_collections` extracts your Directus PostgreSQL table rules so your Mastra AI agent can build custom database execution paths. The framework uses this metadata to decide which database collections require updates during multi-step workflows. After identifying the tables, your Mastra agent runs `list_collection_fields` to map column constraints. If a Directus column configuration changes, the workflow automatically adapts its write payloads via the MCP connection without throwing validation errors.

Safe Directus record mutations via this MCP Server

`patch_cms_record` modifies your Directus database values inside multi-step, conditional Mastra AI workflows. If a database write fails, the workflow engine triggers exponential backoffs to retry the mutation before alerting an administrator. To prevent catastrophic mistakes, you configure manual approvals in Mastra AI before the agent calls `wipe_cms_record`. Honestly, deleting production rows without a human-in-the-loop check is just asking for a bad weekend.

Automated Directus media and user audits

`list_directus_files` verifies Directus media storage metadata inside your automated Mastra AI pipelines. Your agent checks if a newly uploaded asset matches your storage policies before linking it to a database record. Simultaneously, `list_directus_users` monitors active Directus admin identities to audit access rights. The Mastra AI agent flags any suspicious administrative accounts and logs their details using `get_single_item` for security reviews.

Setup guide

Set up Directus 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 Directus 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: "directus-mcp-client",
  servers: {
    "directus-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Directus 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 Directus. 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 Directus 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 Directus MCP in Mastra AI

Configure your agent to catch errors from `patch_cms_record` or `create_cms_record`. Mastra AI automatically retries the tool execution using its built-in exponential backoff mechanism.

Yes, set the `requireToolApproval` flag on the `wipe_cms_record` tool schema. Mastra AI pauses the workflow and waits for your manual confirmation before dropping the row.

Call `get_collection_details` inside your workflow's initialization step. Mastra AI parses the returned properties to construct valid JSON payloads for subsequent database writes.

Run `list_collection_items` to search bounded routing spaces inside your SQL mappers. This filters your dataset and returns only the relevant records to your agent.

Your admin tokens and SQL connection strings never leave the secure Vinkius V8 sandbox. This MCP Server only shares processed JSON payloads from tools like `list_directus_users` over encrypted SSE channels.

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