Patent Connector 1.6 is the biggest release since launch. It does three things at once: it ships the long-promised agentic-AI-first command-line tool, it teaches the connector to handle sound and multimedia trademarks, and it goes back through every office already supported and pulls more out
The most advanced MCP server for patents and trademarks, with the broadest coverage, plus a matching CLI for the terminal. Official patent, trademark and design data, straight from the offices, for Claude, ChatGPT and your shell. One engine, two ways to use it, across six jurisdictions. No scraping, no aggregators,
Originally written in German („Enthusiastische Angst"). While writing this, I listened to one piece, over and over: Mendelssohn's Concerto for Violin, Piano and Strings in D minor, the second movement, the Adagio (Apple Music · Spotify). Take a moment, a small pause - if you feel like it: listen
Patent Connector version 1.5.0 adds three new patent offices: IP Australia, the Japan Patent Office (特許庁), and Taiwan's Intellectual Property Office (經濟部智慧財產局, TIPO). Coverage now reaches across six jurisdictions and three rights - patents, trademarks, and designs - all from official office data, queried with your own API
Almost a year ago I built a small proof of concept: talk to patent offices directly through an MCP server. Then the daily usage started climbing and never stopped. Agentic AI is what tipped it over, and that little experiment quietly became something people now run every day. Today I
Patents are written in a secret language: the kind you get when legalese and engineering specs have a child and let a filing cabinet name it. That is how you end up with classification codes like C02F1/4604, which sounds like a malfunctioning robot but actually means "removing salt
Among patent offices, the USPTO runs one of the most ambitious open-data programs out there. The Open Data Portal (ODP) consolidates what used to be a scatter of legacy hosts into a single, key-authenticated, documented surface: patents, assignments, continuity, office actions, PTAB, bulk datasets. There is a real
After a tough review process, OpenAI just published Patent Connector to the ChatGPT app directory - and I couldn't be more thrilled. Anyone can now add it with a single click, no developer mode required, and with OpenAI's seal of approval that the app is safe and
I added trademark image retrieval to Patent Connector. The MCP specification defines exactly how a server should return images to a client. I implemented it by the book. Then I tested it across clients and the results were all over the place. What the Spec Says The MCP specification defines
Patent Connector version 1.2.0 adds USPTO office action search and trademark lookup tools. These pull data from the new ODP endpoints that USPTO migrated from the legacy Developer Hub. The underlying Go client library was updated to version 1.4 to support these APIs. Office Action Tools You
Version 1.4 of the uspto-odp Go client library adds two major API categories: Office Action search and Trademark Status & Document Retrieval (TSDR). USPTO migrated both from the legacy Developer Hub into the Open Data Portal, and the library now covers all of them. As with previous releases,
Bulk File Loader reached version v1.0.1 with a new data source: the German Patent and Trademark Office (DPMA). The application now downloads bulk patent data from DPMA alongside existing sources, built on top of the dpma-connect-plus Go client library I released earlier. What It Does Bulk
My consulting philosophy: never talk about something you don't fully understand and know. So when MCP came up as a topic, I built a patent MCP server to get real implementation experience. I also found the concept behind MCP very interesting - a standardized protocol for giving LLMs access
I've released a Go client library for the German Patent and Trademark Office's Connect Plus API. The library provides access to all three DPMA services - patents and utility models, designs, and trademarks - through a clean, production-ready interface. Technical Approach No official OpenAPI specification exists for
Thomson Reuters down as much as 18%. RELX down 14%. Wolters Kluwer down 13%. Not because patent attorneys or contract lawyers became obsolete, but because Anthropic showed that the software wrapping their workflows can be replicated with an open-source plugin. The expertise is fine. What's dead is
Starting 2026 with a fresh release: https://github.com/patent-dev/bulk-file-loader is now open source. Bulk File Loader automates downloading patent bulk data from EPO and USPTO. Set it up once, configure your credentials, and let it handle the rest - scheduled syncs, progress tracking, and webhook notifications
USPTO Open Data Portal 3.0 brings full API access to Patent Trial and Appeal Board data - IPR proceedings, trial decisions, appeal outcomes, and interference records going back to 1997. The uspto-odp Go client library has been updated to support all 19 new endpoints.
No single database contains all patent texts. Formats differ between authorities, API access typically requires payment, and OCR introduces errors. This guide explains the challenges of accessing patent text data and what it would take to create a truly open, global resource.
Patent Connector now supports the USPTO Open Data Portal (ODP) API, adding US patent full-text access alongside the existing EPO integration. While EPO provides excellent global coverage, it lacks full-text data for US patents. The new USPTO ODP API integration enables ChatGPT, Claude, and other AI assistants connected
I've built Patent Connector, a Model Context Protocol server now in open beta. It connects ChatGPT Desktop, Claude Desktop, and other MCP-compatible AI tools directly to patent databases - starting with the free EPO OPS API. Instead of manually searching patent databases, copying claims, and pasting them into
I've released a complete Go client for the European Patent Office's Open Patent Services API v3.2. The library provides access to patent bibliographic data, full-text documents, search capabilities, family information, and legal status data. Building on Official Specifications I started with EPO's
I've released a new Go client library for the European Patent Office Bulk Data Distribution Service. The library provides straightforward access to EPO's bulk patent data products through a clean, production-ready Technical Approach Since no official API specification existed for BDDS, I created an OpenAPI
I've released a comprehensive Go client library for the USPTO Open Data Portal API. The library provides complete coverage of all 19 functional endpoints across patent applications, bulk data downloads, and petition decisions. Technical Approach USPTO provides an official Swagger v2 specification for their ODP API. However, the
Great news for patent data enthusiasts! The USPTO has launched its Open Data Portal (ODP), making it faster and easier to access patent and trademark datasets. Whether you're a researcher, developer, or just a data geek, this platform simplifies the way you retrieve and customize USPTO data. The