How to Use the AlgoDocs MCP in Google ADK

Q: How do I configure the AlgoDocs server in Google ADK?

Install the google-adk package via pip. Create a McpToolset using StreamableHttpServerParameters with your endpoint URL. Pass this toolset to your LlmAgent initialization.

Q: Can I restrict which AlgoDocs MCP tools my Google ADK agent sees?

You can pass a toolnames filter when creating the toolset. This prevents the agent from calling administrative endpoints like getmyaccount if you only want it to extract data.

Q: How does Google ADK handle the extracted text from AlgoDocs?

The agent pulls the text via getdocumentdata. Because Gemini supports massive context windows, your agent can hold dozens of parsed PDFs in memory at once for cross-document reasoning.

Feed parsed PDFs directly into your Google ADK agents and analyze massive document batches using Gemini's long context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AlgoDocs MCP to Google ADK

Create your Vinkius account to connect AlgoDocs 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 AlgoDocs with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect AlgoDocs to your Google ADK workflow

The AlgoDocs MCP Server exposes the `upload_document_from_url` tool to send external files into your Gemini-powered agent. Your Google ADK setup grabs the document, parses it, and holds the resulting text in memory for long-context reasoning. Agents monitor the extraction progress using `get_document_status`. When the file is ready, they call `get_document_data` to pull the raw text, which you can then pipe directly into BigQuery or Vertex AI for enterprise storage.

Process bulk data with Gemini

Retrieving massive datasets requires the `list_extractor_data` tool. Your agent pulls thousands of extracted fields at once, feeding them into Gemini models that easily handle massive context windows. You map out your storage backend via `list_folders` and `get_folder_details`. This allows your enterprise agents to organize extracted invoice or contract data before writing it to your Google Cloud infrastructure.

Monitor account usage via MCP Server

Tracking API consumption happens through the `get_api_usage` and `get_my_account` tools. Your agent checks these endpoints to ensure your document parsing volume stays within billing limits. Monitoring recent files happens via `list_recent_documents`. If an agent needs a specific parsing model, it queries `list_extractors` to find the exact ID required for the job.

Setup guide

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

Install the `google-adk` package via pip. Create a `McpToolset` using `StreamableHttpServerParameters` with your endpoint URL. Pass this toolset to your `LlmAgent` initialization.

You can pass a `tool_names` filter when creating the toolset. This prevents the agent from calling administrative endpoints like `get_my_account` if you only want it to extract data.

The agent pulls the text via `get_document_data`. Because Gemini supports massive context windows, your agent can hold dozens of parsed PDFs in memory at once for cross-document reasoning.

The current toolset requires a public link. You must host the file and pass the link to `upload_document_from_url` for the parser to reach it.

The server operates on a zero-trust architecture. Your Word docs and the resulting parsed text pass through an ephemeral sandbox. Vinkius retains zero data after the Google Cloud connection closes.

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