Leafly Strain Scraper is an MCP server that extracts structured cannabis strain data from Leafly.com following a standardized methodology. It implements both regex-based and LLM-powered extraction techniques to collect 66 data points per strain including cannabinoids, terpenes, effects, and flavors. The server handles batch processing with rate limiting, provides fallback mechanisms for missing data, and exports results in CSV or JSON format. Built with Node.js and the Firecrawl API, it requires an API key for authentication and is designed for researchers, developers, and cannabis industry professionals who need reliable, normalized strain information.
No reviews yet. Be the first to review!
Sign in to join the conversation
Scrapes cannabis strain data from Leafly for specified strains. Parameters: strains (array of strings), exportFormat (string: 'csv' or 'json')
Extracts comprehensive cannabis strain data from a specified Leafly page using an LLM-powered approach. Parameters: urls (array of strings), schema (object), prompt (string)
Find function definitions in code files.
Search for text across all code files.
Generate a tree-like structure of the project.
Analyze project dependencies.
Discover React/React Native components.
Generate text using the DeepSeek R1 model.
Summarize text.
Stream text generation.
Generate text using different DeepSeek models.
Process documents to summarize, extract entities, and analyze sentiment.
Query JSON data using JSONPath expressions.
Filter JSON data based on specified conditions.
Save query results to a file.
Compare two JSON datasets.