How to Use the PDF Munk MCP in Google ADK

Q: How do I run PDF Munk template operations in Google ADK?

Your agent uses listtemplates to find the correct template ID. It then passes the required JSON variables to generatepdffromtemplate to build the document.

Q: How do I handle document splitting?

You run the splitpdf tool, which divides a single large document into individual pages. Your agent can then process each page as an independent asset.

Q: How secure are my screenshots and URLs when using PDF Munk with Google ADK?

Every URL processed by generatepdffromurl and every image generated by generatescreenshot is handled in a zero-trust sandbox. The Google ADK client receives the output via an encrypted, temporary stream, and the source files are instantly destroyed.

Feed enterprise BigQuery data into PDF Munk templates directly from your Google ADK pipelines for automated reporting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PDF Munk MCP to Google ADK

Create your Vinkius account to connect PDF Munk to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PDF Munk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise PDF generation from Google ADK data

PDF Munk connects your Gemini models directly to document engines using the `generate_pdf_from_html` tool inside the Google ADK environment. Your agent pulls raw data from BigQuery, formats it, and renders a clean PDF in seconds. For structured corporate styling, your Google ADK agent queries `get_template` to match layout schemas before running `generate_pdf_from_template`.

Automating document compilation with an MCP Server

Combining several reports into a unified document takes a single call to the `merge_pdfs` tool within your Google ADK pipeline. Your agent tracks file locations in Google Cloud Storage and passes them to this MCP Server for compilation. To keep network transfer fast, your Google ADK agent triggers `compress_pdf` to shrink file sizes before exporting to Cloud Storage. This keeps your delivery pipelines fast and resource-efficient.

Visual web captures and image generation

Capturing web-based dashboards is simple with the `generate_screenshot` tool running inside your Google ADK workflow. Your Gemini agent sends the target URL, grabs the image, and can analyze the visual layout using its native multimodal capabilities. When you need static assets, the `generate_image` tool outputs clean files that your Google ADK agent can analyze using multimodal vision. You can also use `add_watermark` to apply security labels to these assets before saving them.

Setup guide

Set up PDF Munk MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with PDF Munk tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="PDF Munk_agent",
    model="gemini-2.0-flash",
    instruction="You have access to PDF Munk tools via MCP.",
    tools=mcp_tools,
)

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 PDF Munk. 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 PDF Munk 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 PDF Munk MCP in Google ADK

Yes, you can pass a filtered list of tool names to the McpToolset constructor. This prevents Gemini from accidentally invoking administrative tools on the MCP Server when it only needs generation capabilities.

Your agent uses `list_templates` to find the correct template ID. It then passes the required JSON variables to `generate_pdf_from_template` to build the document.

Yes, because this MCP Server returns structured outputs, your Google ADK agent can easily parse the resulting PDF metadata within its 1M+ token context window.

You run the `split_pdf` tool, which divides a single large document into individual pages. Your agent can then process each page as an independent asset.

Every URL processed by `generate_pdf_from_url` and every image generated by `generate_screenshot` is handled in a zero-trust sandbox. The Google ADK client receives the output via an encrypted, temporary stream, and the source files are instantly destroyed.

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