au-trademark-trends-mcp

An MCP server for Australian trade mark trends, built on IP Australia's IPGOD open data. Python + DuckDB.

Architecture

5 CSVs (5.2GB) ──→ etl/build_db.py ──→ data/tm.duckdb (915MB) ──→ src/server.py (MCP)
                   DuckDB reads CSV     5 normalised tables       12 tools, 10-500ms
                   directly             + 1 wide table

The ETL runs in about 33 seconds. tm_application is a denormalised wide table - applicant, country, mark text and class count are all flattened into it - so the common query is a single-table scan with no joins.

Related MCP server: mcp-trademark

Setup

python -m venv .venv

.venv\Scripts\python.exe -m pip install -r requirements.txt

Build the database (needs the five CSVs in the project root, about 33 seconds):

.venv\Scripts\python.exe etl\build_db.py

Run the end-to-end test (spawns a real MCP server and makes 19 tool calls through the official client):

.venv\Scripts\python.exe test\smoke.py

Connecting

Claude Code - the repository ships a .mcp.json whose paths are relative to the project root, so a clone works as soon as the dependencies are installed. Start Claude Code in the project directory; the first run asks whether you trust the project's MCP servers. No paths to edit.

To use it from any directory, register it at user scope instead. This needs absolute paths - replace <project path> with your own:

claude mcp add -s user au-trademark-trends -- "<project path>/.venv/Scripts/python.exe" "<project path>/src/server.py"

Claude Desktop has no concept of a project directory, so absolute paths are the only option. Edit %APPDATA%\Claude\claude_desktop_config.json, and note that backslashes must be doubled inside JSON:

{
  "mcpServers": {
    "au-trademark-trends": {
      "command": "<project path>\\.venv\\Scripts\\python.exe",
      "args": ["<project path>\\src\\server.py"]
    }
  }
}

Quit Claude Desktop completely and restart it afterwards - closing the window is not enough, exit it from the system tray.

On Linux and macOS, use .venv/bin/python in place of .venv/Scripts/python.exe.

The 12 tools

Tables

Counting rules and traps

Every tool returns a caveats field. Pass it on when reporting results.

• applications vs class_filings. With no class filter the metric counts applications; with a class filter it counts class filings, so an application covering three classes is counted three times. The metric field says which.

• The trailing period is always incomplete. Data runs through 2026-08. partial_buckets flags the affected periods and charts shade them grey. Do not read the final period as a decline.

• Status is a snapshot, not an examination outcome. dead includes marks that registered and later lapsed or ceased. A high pending share in the last two or three cohorts is expected, not a signal.

• Keyword search covers mark text only, not goods and services text. Mark text exists for 96.3% of applications.

• per_10k_filings is more trustworthy than a raw count. It normalises against total filing volume, separating a real trend from overall market growth.

• Individual applicant names are pseudonymised upstream and cannot be recovered. Only organisation names are real.

• Applicant names match literally. Separate legal entities of one corporate group (aristocrat technologies australia pty ltd and aristocrat technologies inc) appear as separate rows.

• Filings are attributed to the founding applicant, so later assignments do not move them.

• Madrid exports have no destination country. The source records only that a mark went out, so a total is all that is available.

• The CSVs escape quotes with a backslash (\") rather than doubling them, so read_csv needs escape='\' or it fails partway through party_activity.csv.

Not loaded yet

application_events.csv (4.2GB, 31.7M trade mark events) is not loaded. It would unlock adverse examination rates, opposition rates, renewal rates and true stage-by-stage pendency. Adding it is one more block in the ETL - the event types are already confirmed: exam_outcome_adverse 1.36M, published_opp_lodged 26,834, removed_non_use 6,495.

Data source

IP Australia IPGOD (Intellectual Property Government Open Data), updated annually, available from data.gov.au. Drop replacement CSVs in the project root and re-run etl/build_db.py; the server needs no changes.

The source CSVs and the built database are gitignored - 10.4GB in total, well past GitHub's limits. The five files needed are:

application.csv                 720 MB
application_classification.csv  2.0 GB
application_description.csv     451 MB
application_links.csv           271 MB
party_activity.csv              1.8 GB

Licence

The code is MIT - see LICENSE.

That does not extend to the IPGOD data, which IP Australia publishes under its own terms (CC BY 4.0 at the time of writing). Confirm the current licence on the release page before redistributing the data or any derived dataset, and attribute IP Australia as the source.