How to Use the Docamatic MCP in Google ADK

Q: Can Google ADK agents limit which Docamatic tools are exposed?

Yes. You can use the toolnames filter in the McpToolset configuration to restrict access to specific MCP tools, exposing only generatepdffromtemplate or mergemultiplepdfs if you want to limit the agent's capabilities.

Q: How do I check the history of PDFs my agent has generated?

Your agent can call listgenerationhistory to get a list of recently created documents, making it easy to audit what files have been processed in the current session.

Connect Docamatic to your Google ADK agents to generate PDFs and screenshots directly from your BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docamatic MCP to Google ADK

Create your Vinkius account to connect Docamatic to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Docamatic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Convert Google ADK data to PDFs with an MCP Server

`generate_pdf_from_html` is the primary tool your Google ADK agents use to convert raw HTML strings or web URLs into clean PDF files via our MCP server. This lets your Gemini-powered agents pull structured data from BigQuery, format it into HTML, and instantly output a professional document. Because the agent runs within the Google Cloud ecosystem, you can easily pipe these outputs into your storage buckets or send them to clients. The agent handles the tool invocation natively, letting you focus on the logic rather than rendering engines.

Generate business documents from templates

`generate_pdf_from_template` allows your agent to select a pre-made layout like an invoice or packing slip and inject dynamic JSON data. Your agent can query `list_available_builtin_templates` to see what formats are available and then execute the generation in a single step. This eliminates the need to build custom template parsers in Python. The Gemini model handles the mapping from your database schema to the template's expected JSON structure, making document generation entirely hands-off.

Stitch documents and capture web snapshots

`merge_multiple_pdfs` and `take_web_screenshot` give your Google ADK agents the tools to combine multiple PDF files or capture full-page screenshots of live web applications. The agent can take a screenshot of a live dashboard and merge it directly into a monthly PDF report. You can also use `add_elements_to_pdf` to stamp text, dates, or signatures onto the final document. The entire workflow runs within our secure infrastructure, keeping your agent's execution environment clean and fast.

Setup guide

Set up Docamatic 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 Docamatic 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="Docamatic_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Docamatic 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 Docamatic. 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 Docamatic 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 Docamatic MCP in Google ADK

Install the package using pip install google-adk. Then, initialize McpToolset with the Docamatic endpoint URL and pass it to your LlmAgent instance to expose the document tools.

Yes. You can use the tool_names filter in the McpToolset configuration to restrict access to specific MCP tools, exposing only `generate_pdf_from_template` or `merge_multiple_pdfs` if you want to limit the agent's capabilities.

Yes. Your Gemini agents can analyze massive datasets in their 1M+ token context window and then pass the summarized data to `generate_pdf_from_html` to output a clean executive summary.

Your agent can call `list_generation_history` to get a list of recently created documents, making it easy to audit what files have been processed in the current session.

We use a zero-trust model where all HTML templates, JSON payloads, and generated PDFs are isolated in temporary V8 sandboxes. Your enterprise data never persists on our servers and is fully encrypted in transit.

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