Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@PatPub search published patents for solid-state battery cooling systems"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PatPub ingests published USPTO patent grants and applications and serves full-text search through REST and MCP. It converts APS and XML archives to canonical Markdown, stores publication metadata in Parquet, and indexes text with Quickwit.
Search uses a published release that binds index state, metadata, and source generations. The API verifies each hit against that release, reads the matching document from an immutable source pack, and generates snippets. Serving uses stored publication data and has no live dependency on patent-record services.
Requirements: Python 3.11+, Azure CLI, Terraform 1.6+, an Azure subscription with permission to create resources and assign roles, and a USPTO Open Data Portal API key. Choose a globally unique suffix of 5–10 lowercase letters or digits.
az login
cp ingestion.example.toml ingestion.toml
# Set document categories and year ranges in ingestion.toml.
export USPTO_API_KEY='your USPTO ODP key'
python scripts/launch_azure.py --suffix mypub123The launcher creates billable Azure resources, builds two container images in
Azure Container Registry, and starts ingestion. Search becomes available after
the first archive passes validation and its release is published. Private
credentials and Terraform state are stored in .patpub/<suffix>/.
See deployment for configuration, credentials, and updates. Azure is the supported deployment target; Docker Compose hosting is not implemented.
Related MCP server: USPTO Patent MCP Server
One hourly worker handles initial backfill, retries, and new publications. Enabled catalogs are processed from the oldest missing archive to the newest; new weeks wait behind the historical backlog.
The default configuration covers APS grants from 1976–2001, XML grants from 2002 onward, and application publications from 2001 onward. Pre-1976 ingestion is not implemented.
Quickwit uses a file-backed metastore. The worker stops serving during index writes and restarts it for validation. Search is unavailable during writes and cold starts; serving scales from zero to one replica.
Path | Responsibility |
| Archive acquisition, rendering, metadata, checkpoints, and release publication |
| Ingestion container, including both Rust renderers and the Quickwit writer |
| XML and APS renderers |
| Quickwit indexing, source retrieval, snippets, and REST/MCP serving |
| Azure infrastructure |
| Optional Cloudflare gateway for a custom domain |
| Deployment launcher and serving checks |
| Pipeline, release, and search tests |
Install uv and Rust, then run from the repository root:
uv sync --locked --extra dev --extra azure --extra parquet --extra router --extra mcp
uv run python -m pytest
cargo test --locked --manifest-path rust-worker/Cargo.toml
cargo test --locked --manifest-path aps-worker/Cargo.tomlContributing covers focused checks and container integration tests. The documentation index links deployment, operations, client access, and search references.
The software is licensed under Apache License 2.0. Dependencies retain their own licenses; see third-party notices. USPTO data is retrieved separately and remains subject to its applicable terms.
The repository includes small synthetic fixtures. Corpora, archives, source packs, generated indexes, Terraform state, and secrets are excluded from version control.
This server cannot be deployed
EPO/USPTO search, citations, OCR, plus PATSTAT Portfolio Analytics, guarded SQL and Graph Analytics.
SpecProof: Search standards specs with MCP-ready precision.
Patents MCP — wraps the USPTO Open Data Portal (ODP) Patent File Wrapper API
Patent search, USPTO data, patent landscape & pgvector prior-art search for agents.
