How to Use the USPTO API MCP in Mastra AI

Q: How do I conduct a patent search using USPTO API and Mastra AI?

You use the searchpatents tool with your keyword. Since you're in Mastra AI, if the connection fails or the query times out, the system automatically retries the request until it succeeds or notifies an admin.

Q: Can I retrieve trademark details using USPTO API and Mastra AI?

Yes. Use gettrademarkdetails with the serial number. If a required tool fails (e.g., bad format), your workflow engine will catch it, notify you, and stop the process before corrupting data.

Q: How do I list patent classes using USPTO API and Mastra AI?

Call listpatentclasses at the start of your process. This provides the full scope dictionary you can then use to build more precise search parameters for later tools.

Q: Does this MCP Server support searching US trademarks with USPTO API and Mastra AI?

It does. You run searchtrademarks in your workflow. If the keyword search is successful, you can chain that result into gettrademarkdetails for a full audit.

Build reliable, multi-step IP audit workflows with Mastra AI and MCP Server.

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 Mastra AI

Create your Vinkius account to connect USPTO API to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Patent Discovery

You can start by running `check_api_status` to validate the USPTO Open Data API connection. If that check passes, you can then execute a search using `search_patents`. The workflow handles failures gracefully, automatically retrying if the first attempt fails. This is ideal for critical IP audits where failure isn't an option. Mastra AI builds the necessary reliability into multi-step processes, ensuring your complex business logic runs to completion.

Full Trademark Record Retrieval

Need deep details on a trademark? The `get_trademark_details` tool fetches all records for a specific serial number. If the initial search using `search_trademarks` provided enough info, you can chain that into this detail retrieval. This sequential process is perfect for building workflows where one action (the search) validates and feeds data to the next step (the detailed record pull).

Systematic IP Classification

Start with `list_patent_classes` to map out the entire field of patent codes. Then, if you need to find patents within a specific group, you run `search_patents`, using the list as context for your keywords. This mechanism lets you build an audit path: check scope (classes) -> narrow focus (keyword search) -> confirm details (`get_patent_details`). Mastra AI makes these conditional branches easy.

Setup guide

Set up USPTO API MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All USPTO API tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "uspto-api-mcp-client",
  servers: {
    "uspto-api-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "USPTO API Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to USPTO API tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent USPTO API transactions"
);
console.log(result.text);

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 Mastra AI

You use the `search_patents` tool with your keyword. Since you're in Mastra AI, if the connection fails or the query times out, the system automatically retries the request until it succeeds or notifies an admin.

This server handles Patent and Trademark records. Because these are sensitive Intellectual Property (IP) documents, always ensure your workflow includes appropriate logging and access controls.

Yes. Use `get_trademark_details` with the serial number. If a required tool fails (e.g., bad format), your workflow engine will catch it, notify you, and stop the process before corrupting data.

Call `list_patent_classes` at the start of your process. This provides the full scope dictionary you can then use to build more precise search parameters for later tools.

It does. You run `search_trademarks` in your workflow. If the keyword search is successful, you can chain that result into `get_trademark_details` for a full audit.

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