# Patent Search MCP — AI Agent Patent Intelligence (`red.cars/patent-search-mcp`) Actor Search patents across USPTO, EPO, and Google Patents for AI agents. One tool call to find patents, citations, and company landscapes. - **URL**: https://apify.com/red.cars/patent-search-mcp.md - **Developed by:** [AutomateLab](https://apify.com/red.cars) (community) - **Categories:** Developer tools, Other - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing Pay per usage This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-usage ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Patent Search MCP Server > Search patents across USPTO, EPO, and Google Patents for AI agents. **[View on Apify](https://apify.com/red.cars/patent-search-mcp)** | **[MCP Endpoint](https://patent-search-mcp.apify.actor/mcp)** --- ### What It Does Give AI agents the ability to search patent databases, analyze patent landscapes, and trace citation chains — with one tool call. - **USPTO patents** — full US patent database search - **EPO patents** — European Patent Office search - **Google Patents** — aggregated patent data with citations - **Company landscapes** — full patent portfolios by assignee - **Citation tracking** — forward and backward citations --- ### Quick Start Add to your AI agent: ```json { "mcpServers": { "patent-search-mcp": { "url": "https://patent-search-mcp.apify.actor/mcp" } } } ```` Or with authentication: ```json { "mcpServers": { "patent-search-mcp": { "url": "https://patent-search-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN" } } } ``` *** ### Tools | Tool | Price | Description | |------|-------|-------------| | `search_patents` | $0.05 | Search by keyword, CPC code, or inventor | | `get_patent_details` | $0.03 | Full metadata, claims, assignee | | `find_patent_citations` | $0.05 | Forward/backward citation chain | | `patent_landscape_by_company` | $0.10 | Company patent portfolio + filing trends | *** ### Example Calls #### Search Patents ``` search_patents(query="neural network transformer", max_results=10) ``` Returns: ```json { "patent_number": "US10712345B2", "title": "Attention mechanism for neural networks", "inventors": ["Vaswani", "Shazeer"], "filing_date": "2017-06-12", "issue_date": "2020-08-25", "assignee": "Google LLC", "source": "USPTO", "url": "https://patents.google.com/patent/US10712345B2" } ``` #### Get Patent Details ``` get_patent_details(patent_number="US10123456", source="all") ``` Returns: ```json { "patent_number": "US10123456", "title": "Medical device with sensor array", "abstract": "A medical device comprising...", "assignee": "Medtronic PLC", "source": "Google Patents", "url": "https://patents.google.com/patent/US10123456", "details_available": true } ``` #### Find Citations ``` find_patent_citations(patent_number="US10712345B2", citation_type="forward") ``` Returns: ```json { "patent_number": "US10712345B2", "forward_citations": [ {"patent_number": "US11012345", "source": "forward_citation"}, {"patent_number": "EP3456789", "source": "forward_citation"} ], "total": 156 } ``` #### Company Landscape ``` patent_landscape_by_company(company_name="Apple Inc", max_results=20) ``` Returns: ```json { "company_name": "Apple Inc", "total_patents": 247, "filing_trend": {"2020": 45, "2021": 52, "2022": 61, "2023": 89}, "top_patents": [...], "technology_areas": ["semiconductor", "display", "wireless"], "sources_searched": ["USPTO", "Google Patents"] } ``` *** ### How It Works **Phase 1: Multi-Source Search** - Queries USPTO Patent Public Search API - Queries Google Patents - Queries EPO Open Patent Services (OPS) - All queries run in parallel for speed **Phase 2: Deduplication** - Removes duplicate patents by number - Preserves first-seen metadata **Phase 3: Aggregation** - Returns structured JSON with source attribution - Includes direct URLs to patent records *** ### Data Sources | Source | Coverage | Type | |--------|----------|------| | USPTO | 12M+ US patents | Full text search | | EPO | 100M+ worldwide | Patent families | | Google Patents | Aggregated | Citations, assignments | *** ### Use Cases #### Tech Transfer Evaluation *"Find patents from MIT researchers in the AI space"* → AI calls `search_patents` with MIT inventor query → Returns MIT patent portfolio #### Due Diligence *"What's Apple's patent strategy in electric vehicles?"* → AI calls `patent_landscape_by_company` → Returns filing trends, top patents #### Citation Analysis *"Who has cited the original transformer patent?"* → AI calls `find_patent_citations` with citation\_type="forward" → Returns citing patents #### Freedom to Operate *"Are there blocking patents on our surgical robot design?"* → AI calls `search_patents` with design keywords → Returns relevant patents *** ### Pricing | Tool | Price | |------|-------| | `search_patents` | $0.05/call | | `get_patent_details` | $0.03/call | | `find_patent_citations` | $0.05/call | | `patent_landscape_by_company` | $0.10/call | No subscription required. Pay per use via Apify PPE. *** ### Cross-Sell Triggers This MCP complements the research intelligence cluster: - `university-research-mcp` → `patent_landscape` triggers → `patent-search-mcp` - `academic-research-mcp` → `find_citations` on patents → `find_patent_citations` - `healthcare-compliance-mcp` → FDA device approvals → patent history check *** ### Connect to AI Agents #### Claude Desktop ```json { "mcpServers": { "patent-search-mcp": { "url": "https://patent-search-mcp.apify.actor/mcp" } } } ``` #### Cursor / Windsurf Add the same JSON to your AI client config. #### cURL Example ```bash curl -X POST "https://patent-search-mcp.apify.actor/mcp" \ -H "Content-Type: application/json" \ -d '{"tool": "search_patents", "params": {"query": "neural network", "max_results": 5}}' ``` *** ### Output Schema All tools return JSON. Each result includes: - `patent_number` — unique identifier - `title` — patent title - `source` — which database - `url` — direct link to record *** ### API Status - **Health**: Running - **Uptime**: 99.9% - **Rate Limits**: Respect upstream API limits - **Support**: Open issue on GitHub # Actor input Schema ## `tool` (type: `string`): MCP tool to call ## `params` (type: `object`): Tool parameters as JSON object ## Actor input object example ```json { "tool": "search_patents", "params": { "query": "machine learning", "max_results": 1 } } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "tool": "search_patents", "params": { "query": "machine learning", "max_results": 1 } }; // Run the Actor and wait for it to finish const run = await client.actor("red.cars/patent-search-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "tool": "search_patents", "params": { "query": "machine learning", "max_results": 1, }, } # Run the Actor and wait for it to finish run = client.actor("red.cars/patent-search-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "tool": "search_patents", "params": { "query": "machine learning", "max_results": 1 } }' | apify call red.cars/patent-search-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=red.cars/patent-search-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Patent Search MCP — AI Agent Patent Intelligence", "description": "Search patents across USPTO, EPO, and Google Patents for AI agents. One tool call to find patents, citations, and company landscapes.", "version": "1.0", "x-build-id": "JSo4AtBfShLjrNq2F" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/red.cars~patent-search-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-red.cars-patent-search-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/red.cars~patent-search-mcp/runs": { "post": { "operationId": "runs-sync-red.cars-patent-search-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/red.cars~patent-search-mcp/run-sync": { "post": { "operationId": "run-sync-red.cars-patent-search-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "tool": { "title": "Tool Name", "enum": [ "search_patents", "get_patent_details", "find_patent_citations", "patent_landscape_by_company" ], "type": "string", "description": "MCP tool to call" }, "params": { "title": "Parameters (JSON)", "type": "object", "description": "Tool parameters as JSON object" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```