How to Use the Gotenberg MCP in CrewAI

Q: How do I add the Gotenberg MCP Server to my CrewAI agents?

Pass your Vinkius server URL directly into the mcps list when defining your CrewAI agent. The framework automatically connects over HTTP and exposes tools like converthtmltopdf to that specific agent.

Q: Can I restrict specific Gotenberg tools to only certain CrewAI agents?

Yes, you can use MCPServerHTTP from crewai.mcp along with a toolfilter to expose only selected MCP tools. This allows you to give your designer agent access to converturltopdf while restricting your editor agent to writepdfmetadata.

Q: How do CrewAI agents collaborate on long PDF merging tasks using Gotenberg?

A research agent can convert multiple sources using convertofficetopdf, and then pass the file paths to a coordinator agent. That coordinator agent then calls mergepdfs to produce a single unified document.

Q: What happens if a CrewAI agent encounters an invalid PDF in Gotenberg?

When a tool like readpdfbookmarks fails due to a corrupted file, the error is returned to the agent's memory. The agent can then use its reasoning capabilities to attempt a repair or alert the crew moderator.

Deploy specialized agent crews to generate, audit, and split enterprise documents using Gotenberg and CrewAI.

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 CrewAI

Create your Vinkius account to connect Gotenberg to CrewAI — 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run multi-agent PDF production in CrewAI

Set up a specialized crew where one agent drafts reports in markdown and another agent converts them using `convert_markdown_to_pdf`. CrewAI coordinates the handoff, ensuring that raw text is formatted correctly before the conversion tool is invoked. You can also assign a supervisor agent to run `read_pdf_metadata` on the generated file to verify compliance. If the metadata is missing required tags, the supervisor can task another agent to apply them with `write_pdf_metadata`.

Automate document assembly and verification

Your crew can split massive reports into manageable sections using `split_pdf` so individual agents can analyze them in parallel. Once the analysis is complete, a coordinator agent can run `merge_pdfs` to compile the final verified report. To ensure visual accuracy, have an auditor agent take a screenshot using `screenshot_html` or `screenshot_url`. This lets your agents inspect the generated output against design guidelines before delivering it to the user.

Embed attachments and structure bookmarks

Give your agents the ability to package supporting files directly into your primary deliverables using `embed_pdf_attachments`. A CrewAI researcher agent can gather raw CSV data, while a compiler agent embeds it directly into the final PDF. You can also use `write_pdf_bookmarks` to build structured navigation tables for long documents. This ensures that the final output delivered by your crew is organized and easily readable by human stakeholders.

Setup guide

Set up Gotenberg MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Gotenberg tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Gotenberg Analyst",
    goal="Access and analyze Gotenberg data via MCP.",
    backstory="Expert analyst with direct Gotenberg access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Gotenberg transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Gotenberg Analyst",
        goal="Access and analyze Gotenberg data via MCP.",
        backstory="Expert analyst with direct Gotenberg access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Gotenberg transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius server URL directly into the `mcps` list when defining your CrewAI agent. The framework automatically connects over HTTP and exposes tools like `convert_html_to_pdf` to that specific agent.

Yes, you can use `MCPServerHTTP` from `crewai.mcp` along with a `tool_filter` to expose only selected MCP tools. This allows you to give your designer agent access to `convert_url_to_pdf` while restricting your editor agent to `write_pdf_metadata`.

A research agent can convert multiple sources using `convert_office_to_pdf`, and then pass the file paths to a coordinator agent. That coordinator agent then calls `merge_pdfs` to produce a single unified document.

When a tool like `read_pdf_bookmarks` fails due to a corrupted file, the error is returned to the agent's memory. The agent can then use its reasoning capabilities to attempt a repair or alert the crew moderator.

No, this MCP Server operates on a zero-trust model where all file bytes, HTML templates, and URLs are processed in ephemeral sandboxes. Once the tool execution finishes, all temporary document data is permanently purged from memory.

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