How to Use the Contentful MCP in Mastra AI

Q: How do I register Contentful tools in a Mastra AI agent?

Import the client from @mastra/mcp and pass the server URL. You can then retrieve the tool definitions and spread them directly into your agent's tools configuration, allowing immediate access to operations like listentries.

Q: Can a Mastra AI workflow query multiple Contentful spaces?

Yes. The agent can programmatically call listspaces and listorganizations to map out your entire account structure, then route specific content updates to different environments based on your business logic.

Q: Does Mastra AI support human approval before modifying Contentful?

Yes, you can configure requireToolApproval on critical write operations. The workflow will pause when the agent attempts to run publishentry or updateentry, resuming only after manual confirmation.

Build self-healing Mastra AI workflows that automatically update, structure, and publish Contentful entries with built-in retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contentful MCP to Mastra AI

Create your Vinkius account to connect Contentful 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 Contentful with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step CMS workflows with Mastra AI

Mastra AI shines when things get complicated. If a content migration fails halfway through, your MCP agent can catch the error, run `unpublish_entry` to rollback the changes, and retry the operation with exponential backoff. You write the logic in TypeScript, defining strict steps for how the agent should handle `create_entry` or `update_entry`. The built-in workflow engine ensures your CMS state never gets stuck in an inconsistent draft loop.

Automatic schema validation via MCP Server

Guard your production spaces from malformed data. Before running any write operations, this MCP Server lets your Mastra AI agent execute `get_content_type` to verify fields against your actual Contentful validation rules. If the agent tries to push a string into a number field, the workflow catches it. The agent can then correct its own payload and retry `update_entry` without failing the entire automated pipeline.

Human-in-the-loop publishing

You don't have to trust the agent to publish live changes blindly. Use Mastra AI's approval gates to halt execution after the agent calls `create_entry` and before it triggers `publish_entry`. The workflow pauses, notifies your team, and waits for a manual sign-off. Once approved, the agent resumes and completes the publish step, keeping your production site safe.

Setup guide

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

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

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

Import the client from `@mastra/mcp` and pass the server URL. You can then retrieve the tool definitions and spread them directly into your agent's `tools` configuration, allowing immediate access to operations like `list_entries`.

Yes. The agent can programmatically call `list_spaces` and `list_organizations` to map out your entire account structure, then route specific content updates to different environments based on your business logic.

Mastra AI has a built-in workflow engine that handles rate limits gracefully. If a call to `list_assets` or `get_entry` triggers a 429 limit, the framework backs off and retries automatically.

Yes, you can configure `requireToolApproval` on critical write operations. The workflow will pause when the agent attempts to run `publish_entry` or `update_entry`, resuming only after manual confirmation.

Absolutely. Your space schemas, asset details, and draft entries are processed in real-time inside an ephemeral V8 sandbox via the MCP gateway. Zero data is cached or logged, keeping your proprietary content models completely private.

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