How to Use the Gotenberg MCP in LangChain

Q: Can LangChain agents handle complex document conversions using Gotenberg?

Yes, you can trigger convertofficetopdf or converturltopdf within any agentic step. The agent manages the input and receives the base64 encoded PDF output for further processing.

Q: Does Gotenberg work with LangChain for multi-step reasoning?

Absolutely, as you can link tools like mergepdfs to follow a conversion tool. The agent determines the correct sequence based on the chain's requirements.

Q: How does the Gotenberg MCP Server handle document attachments?

The embedpdfattachments tool allows your agent to attach supplementary files to a primary PDF. You define the logic in your chain to determine which files to embed.

Use the Gotenberg MCP Server to turn raw HTML, Markdown, and Office files into PDF chains directly inside your LangChain agents.

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 LangChain

Create your Vinkius account to connect Gotenberg to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate document pipelines in LangChain

Chain together document generation tasks by piping outputs directly into your agent logic. You can use `convert_html_to_pdf` to generate reports and immediately feed the result into other vector store operations. This workflow lets your agents handle multi-step document creation without manual intervention. Each step is traceable through your existing LangSmith infrastructure for full visibility.

Dynamic PDF manipulation via MCP Server

Control your PDF structure programmatically by integrating `merge_pdfs` and `split_pdf` into your agentic chains. Your agents can now parse source files, reorder pages, and assemble custom documents on the fly. These tools operate within your chain, allowing the agent to decide when to combine or separate data based on the task at hand. It removes the need for external scripts when handling document assembly.

Metadata and bookmark management

Inject structured data into your generated PDFs using `write_pdf_metadata` and `write_pdf_bookmarks` during the agent execution loop. This ensures every document your agent produces is indexed and searchable from the moment of creation. Your agents can also read existing file properties using `read_pdf_metadata` to inform future decisions in the chain. It keeps your document lifecycle consistent with your data storage standards.

Setup guide

Set up Gotenberg MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Gotenberg tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gotenberg-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Gotenberg transactions"
    })
    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 LangChain

Install the necessary MCP adapters and initialize the client using the server's HTTP endpoint. Once connected, fetch the tools and pass them into your agent constructor to enable document processing.

Yes, you can trigger `convert_office_to_pdf` or `convert_url_to_pdf` within any agentic step. The agent manages the input and receives the base64 encoded PDF output for further processing.

Absolutely, as you can link tools like `merge_pdfs` to follow a conversion tool. The agent determines the correct sequence based on the chain's requirements.

The `embed_pdf_attachments` tool allows your agent to attach supplementary files to a primary PDF. You define the logic in your chain to determine which files to embed.

Data is processed ephemerally within the server sandbox. The Gotenberg MCP Server does not store your documents, ensuring that raw file contents remain isolated from persistent storage.

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