How to Use the Gotenberg MCP in Mastra AI

Q: Can I require human approval before Mastra AI triggers a Gotenberg conversion?

Yes, you can use Mastra AI's requireToolApproval feature on tools like writepdfbookmarks or metadata tools. This pauses the workflow and waits for a human to confirm the changes before writing to the PDF.

Q: How does Mastra AI handle errors when Gotenberg fails to convert a URL?

If converturltopdf encounters a network timeout, Mastra AI's built-in workflow engine uses automatic retries. You can define custom backoff rules so your agent doesn't spam the server.

Automate complex multi-step PDF generation workflows with Mastra AI and this high-performance MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Gotenberg MCP to Mastra AI

Create your Vinkius account to connect Gotenberg to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Gotenberg with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build resilient PDF pipelines in Mastra AI

Mastra AI lets you build multi-step pipelines using this MCP Server that handle document generation failures gracefully. If a call to `convert_office_to_pdf` fails because of a malformed document, your workflow can automatically catch the error and retry with exponential backoff. You can also configure conditional branches to check the MCP Server status via `get_health` before starting large batch runs. This ensures your automated pipelines never waste API calls or crash mid-execution when resources are tight.

Extract and route document metadata automatically

Your agents can inspect incoming files using `read_pdf_metadata` to determine the next step in a Mastra AI workflow. For example, if a document lacks a valid author tag, the workflow branches to a step that automatically applies one using `write_pdf_metadata`. You can also use `read_pdf_bookmarks` to extract structural outlines from large documents. This allows your Mastra AI agents to parse chapters and split files intelligently using `split_pdf` based on actual document structure.

Generate dynamic reports from markdown inputs

Pass dynamic markdown templates directly to `convert_markdown_to_pdf` as part of your automated workflow steps. Mastra AI manages the state between tasks, feeding structured database outputs into the Gotenberg engine to generate polished PDF files. If you need to verify the layout, use `screenshot_markdown` to generate a quick preview image. This setup lets your agents run automated visual checks on generated reports before sending them to clients.

Setup guide

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

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

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

Instantiate the client with your Vinkius HTTP endpoint, then call `mcpClient.listTools()` to retrieve the tool definitions. You can then spread these tools directly into your Mastra AI agent configuration.

Yes, you can use Mastra AI's `requireToolApproval` feature on tools like `write_pdf_bookmarks` or metadata tools. This pauses the workflow and waits for a human to confirm the changes before writing to the PDF.

If `convert_url_to_pdf` encounters a network timeout, Mastra AI's built-in workflow engine uses automatic retries. You can define custom backoff rules so your agent doesn't spam the server.

Yes, Mastra AI workflows support parallel step execution. You can run multiple instances of `convert_html_to_pdf` simultaneously and then pipe all outputs into `merge_pdfs` as a final step.

Your source HTML, markdown, and PDF bytes are processed entirely in memory within Vinkius's zero-trust sandboxes. No document data is ever written to persistent storage, ensuring your private business reports remain completely confidential.

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