MCP

Whether your assistant of choice is ChatGPT or Claude, the Model Context Protocol is how it reaches Patalyze. There are two servers to point it at, and they do different jobs:

• Global Patents gives an assistant eyes: read-only search over the global patent corpus and CPC/IPC classifications. It never touches your research databases.
• Patalyze gives an agent hands: full read and write access to your research databases (products, patents, claim mappings, dashboards and notes), acting with your permissions.

Start with Global Patents. It's one URL and four read-only tools, so there is nothing to configure and nothing it can break, and patent search is usually the first thing you want from an assistant anyway. Add the Patalyze server when you're ready for an agent that works inside your databases.

Both servers are remote HTTP endpoints that authenticate with your Patalyze account over OAuth: add the URL in your client, sign in in the browser, approve access. No API keys to manage.

Global Patents MCP#

Read-only search over the global patent corpus and CPC/IPC classifications. Because it never touches your research databases, it's the safe first install: connect it and immediately ask about prior art, a competitor's filings, or what a CPC class actually covers. It stays useful alongside the Patalyze server later, for quick lookups mid-research.

During authorization the server requests:

• patents:read to search and read patents.
• classifications:read to search CPC/IPC classifications.

It exposes four tools:

• search-patents searches the global corpus with text, bibliographic filters and semantic similarity.
• get-patent returns a single patent by publication number.
• search-classifications searches CPC/IPC classifications by symbol, text or meaning.
• get-classification returns a classification and its tree by symbol.

Patalyze MCP#

The full workbench. This server opens your research databases to an MCP client: products, patents, patent-to-product mappings, dashboards, charts and notes. An agent acts with your permissions and can both read and edit; this is the server that lets an assistant build out a research database end to end.

During authorization the server requests:

• research:read and research:write to read and modify your databases.
• patents:read and classifications:read to search the global patent corpus and classifications.

The server exposes about 40 tools, grouped by what they act on:

• Research databases: list, create, rename, move and delete databases and library folders.
• Patents: search the global corpus, add or remove patents, and read a patent with its mappings.
• Products: add a product (optionally crawling its website), update attributes and descriptions, and delete products.
• Mappings: create, edit and delete patent-to-product claim mappings.
• Pages: create table, note and dashboard pages, configure table views, edit notes, and add or update charts.
• Status: track background jobs such as website crawls and mapping runs.

Connect any MCP client#

Any client that supports remote MCP servers over HTTP with OAuth can connect. The servers are independent, so add one or both. Point the client at a server URL above; adding it starts an OAuth flow where you sign in to Patalyze and approve access. Many clients accept a JSON config like:

{
  "mcpServers": {
    "global-patents": {
      "type": "http",
      "url": "https://search.patalyze.com/mcp"
    },
    "patalyze": {
      "type": "http",
      "url": "https://api.patalyze.com/mcp"
    }
  }
}