How to Use the PDF.co MCP in Google ADK

Q: How do I connect the PDF.co MCP Server to my Google ADK agent?

Initialize the McpToolset with the Vinkius MCP transport URL. Pass this toolset into your LlmAgent constructor to give your Gemini models access to all 12 document tools.

Q: Can my Google ADK agent check my remaining PDF.co credits?

Yes. The agent can invoke getaccountinfo to check your current balance and credit usage, allowing you to build automated alerts or pause pipelines if credits run low.

Q: How do PDF.co and Google ADK handle scanned documents?

The agent automatically routes scanned files through ocrimage or runs extractpdfmeta to pull structured metadata, bypasses binary limits, and feeds the output directly to Gemini.

Q: Is there a way to filter tools in the Google ADK setup?

Yes. You can use the toolnames filter in the McpToolset parameters to restrict your agent's access to specific tools like pdftojson while hiding modification tools.

Run high-volume PDF parsing directly from BigQuery using the PDF.co MCP Server and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PDF.co MCP to Google ADK

Create your Vinkius account to connect PDF.co 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.co with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Feed Gemini long-context windows with clean text

Gemini excels at massive context windows, but feeding raw binary files is messy and expensive. Use `pdf_to_text` to extract clean, structured strings from huge documents and dump them straight into your prompt context. If you are dealing with scanned invoices or image-heavy reports, the `ocr_image` tool converts those pixels into readable text first. This lets your agent process millions of tokens without wasting compute on image recognition.

Enterprise data pipeline integration with Google ADK

Connect your document workflows to your cloud warehouse via MCP. Your agent can read incoming files, run `pdf_to_csv` to isolate tables, and write the structured data directly into BigQuery tables for analytics. For complex layouts, `pdf_to_json` gives you precise coordinate data. Your enterprise agent can map out exactly where headers and line items sit, making it easy to validate documents against your database schemas.

High-speed batch processing and merging

When dealing with thousands of individual records, you need to consolidate. Have your agent call `merge_pdfs` to bundle daily reports into single files before archiving them in Google Cloud Storage. If a document contains too much noise, your agent can run `split_pdf` to isolate the exact pages you need. This keeps your processing pipeline fast and prevents Gemini from getting bogged down in irrelevant pages.

Setup guide

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

Initialize the `McpToolset` with the Vinkius MCP transport URL. Pass this toolset into your `LlmAgent` constructor to give your Gemini models access to all 12 document tools.

Yes. The agent can invoke `get_account_info` to check your current balance and credit usage, allowing you to build automated alerts or pause pipelines if credits run low.

The agent automatically routes scanned files through `ocr_image` or runs `extract_pdf_meta` to pull structured metadata, bypasses binary limits, and feeds the output directly to Gemini.

Yes. You can use the `tool_names` filter in the `McpToolset` parameters to restrict your agent's access to specific tools like `pdf_to_json` while hiding modification tools.

Your binary files remain in your secure Google Cloud Storage buckets. The MCP server only accesses them via signed URLs, processes them in memory, and returns the parsed text, CSV, or XML data.

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