How to Use the USPTO API MCP in Google ADK

Q: How do I use USPTO API with the Google ADK to search US patents?

The agent uses searchpatents as a tool. It takes your keywords, gets the patent list, and because you're in the Gemini ecosystem, it can then reason over massive context blocks containing all those search results.

Q: Can I use USPTO API with the Google ADK to get specific trademark details?

Yes. Call gettrademarkdetails and pass the serial number directly. The agent gets the full data, which you can then write immediately into a BigQuery table for longitudinal analysis.

Q: Does USPTO API with the Google ADK support checking service status?

It does. Running checkapistatus is the first thing your agent should do. It confirms the external data source is live before attempting any resource-intensive searches or detail retrievals.

Q: Is it possible for Google ADK to use USPTO API to list all available patent classes?

You can absolutely use listpatentclasses. This gives your agent a master list of codes, allowing you to restrict future searches and make your IP audit incredibly precise.

Build enterprise IP auditing agents and process patent data with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USPTO API MCP to Google ADK

Create your Vinkius account to connect USPTO API 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 USPTO API with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Big Context Patent Research

The tool `search_patents` allows your agent to query US patents using keywords. Since you're building on the Gemini models, these search results feed into a massive context window (1M+ tokens), letting you analyze huge amounts of related text. After finding initial matches via keyword sweeps, you can run `get_patent_details` for deep dives. The agent processes this detailed data alongside your existing BigQuery data.

Structured Trademark Audits

Use `search_trademarks` to find US trademarks by keyword, providing a clear list of potential overlaps. This initial sweep is perfect for populating structured datasets in BigQuery. The agent then calls `get_trademark_details` on any returned serial number. The native integration with Google Cloud means this metadata writes directly into your enterprise data model.

Comprehensive IP Workflow

You can build a multi-step process using the MCP Server. Start by calling `list_patent_classes` to map out the entire patent landscape, then use that knowledge in conjunction with `search_patents`. This structured approach prevents missed data points. This whole sequence—listing classes, searching patents, and getting details—executes reliably within your Google ADK agent framework.

Setup guide

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

The agent uses `search_patents` as a tool. It takes your keywords, gets the patent list, and because you're in the Gemini ecosystem, it can then reason over massive context blocks containing all those search results.

Yes. Call `get_trademark_details` and pass the serial number directly. The agent gets the full data, which you can then write immediately into a BigQuery table for longitudinal analysis.

It does. Running `check_api_status` is the first thing your agent should do. It confirms the external data source is live before attempting any resource-intensive searches or detail retrievals.

This MCP Server deals with patent numbers and trademark serial numbers. The core data type is descriptive text (keywords) linked to the structured records of US patents and trademarks.

You can absolutely use `list_patent_classes`. This gives your agent a master list of codes, allowing you to restrict future searches and make your IP audit incredibly precise.

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