How to Use the Gotenberg MCP in AutoGen

Q: How do agents verify Gotenberg tool outputs in AutoGen?

Agents can use gethealth to verify server availability before starting a task. If a conversion fails, they can discuss the error and attempt a different approach.

Build consensus-driven document workflows by letting AutoGen agents debate and execute Gotenberg MCP Server tasks.

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 AutoGen

Create your Vinkius account to connect Gotenberg to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-agent document conversion workflows

Let your agents debate the best conversion parameters for `convert_office_to_pdf` before executing the task. This ensures your documents are formatted correctly based on peer-reviewed agent decisions. One agent can handle the conversion while another validates the output quality. It creates a robust check-and-balance system for your reporting pipeline.

Gotenberg MCP Server for agentic deliberation

Use `merge_pdfs` and `split_pdf` as tools in an AutoGen conversation to handle complex document assembly. Your agents can negotiate the structure of the final PDF based on specific business requirements. This prevents errors by forcing agents to reach a consensus before modifying your production files. The process is fully transparent within your agent chat history.

Automated PDF metadata and bookmarking

Coordinate agents to write metadata and bookmarks using `write_pdf_metadata` and `write_pdf_bookmarks` as part of the document finalization process. Agents can challenge each other on tag accuracy before committing changes to the PDF. This ensures your documents adhere to internal standards before they are finalized. Your agents ensure every file is properly categorized and indexed.

Setup guide

Set up Gotenberg MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Gotenberg tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Gotenberg_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Gotenberg data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Gotenberg_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Gotenberg data")
    print(result.messages[-1].content)

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 AutoGen

Use the autogen-ext library to register the Gotenberg MCP Server tools. Once registered, pass the list to your AssistantAgent to make them available for the agents to discuss.

Yes, agents can debate which files to merge and in what order. They then call the `merge_pdfs` tool to perform the action once they agree.

It does. You can provide the tools to one or multiple agents, allowing for complex decision-making processes regarding your PDF generation needs.

Agents can use `get_health` to verify server availability before starting a task. If a conversion fails, they can discuss the error and attempt a different approach.

The server processes your data in an isolated environment and does not persist your documents. Every document generated by Gotenberg is treated as a transient object, ensuring your information remains secure.

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