patentorney-mcp
Manages patent application drafts via structured YAML and LaTeX sections, with tools for claims, figures, numerals, prior art, glossary, and export.
README
patentorney-mcp
An MCP server for managing patent application drafts. Built with FastMCP and designed for use with AI coding assistants (Windsurf, Claude Desktop, etc.).
Installation
pip install patentorney-mcp
Or with uvx (no install needed):
uvx patentorney-mcp
MCP Client Configuration
For Windsurf / Claude Desktop, add to your MCP config:
{
"mcpServers": {
"patentorney-mcp": {
"command": "uvx",
"args": ["patentorney-mcp"]
}
}
}
On first use, call set_root(path='/absolute/path/to/project') to point the server at the directory containing patent.yaml. All other tools will prompt for this if it hasn't been set.
Tools (8)
| Tool | Purpose |
|---|---|
set_root(path) |
Point at a patent project directory. Must be called first. |
guide(topic?) |
Usage guides. No args → index. |
claim(action, ...) |
Claims: add|get|update|remove|move|rename|tree |
figure(action, ...) |
Figures: add|get|update|remove|move|rename|list |
numeral(action, ...) |
Numerals: add|get|update|remove|lookup|rename|renumber|list |
prior_art(action, ...) |
Prior art & IDS: add|get|update|remove|list|ids_add|ids_list|ids_check |
glossary(action, ...) |
Glossary: add|get|update|remove|list |
export(target, ...) |
Status, validation & export: status|check|claims|drawings_description|claims_latex|drawings_latex|latex |
Any tool called before set_root() returns an error with a hint to call it. All errors include LLM-actionable hints.
Architecture
patent.yaml— single source of truth for structured data (claims, numerals, figures, glossary, prior art)sections/*.tex— prose sections edited directly;claims.texanddrawings-description.texare generated- Stable slug IDs — all entities use kebab-case slugs; presentation numbers computed from list order
- Dual addressing — tools accept slug or current number (e.g.,
claim("get", id="3")orclaim("get", id="mof-synthesis-method")) - File locking —
fcntl.flockfor safe concurrent access from multiple server instances - Structured claims — preamble + transitional + elements (each with numeral associations)
Project Layout
my-patent/
├── patent.yaml # structured data (MCP-managed)
├── sections/
│ ├── field.tex # prose (edit in IDE)
│ ├── background.tex # prose
│ ├── detailed-description.tex # prose
│ ├── abstract.tex # prose
│ ├── claims.tex # GENERATED
│ └── drawings-description.tex # GENERATED
├── figures/
│ └── *.pdf
├── main.tex # document root
└── tome/ # prior art library (optional)
Testing
uv run pytest
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.