Model-Context-Protocol Servers

What is Model-Context-Protocol Servers?

A collection of purpose-built Model Context Protocol (MCP) servers for web scraping and structured data extraction, codebase navigation and analysis, LLM-powered text generation, and JSON querying. Each server exposes its capabilities as MCP tools and resources, making them composable building blocks for AI agent workflows. The servers span TypeScript and Python/JavaScript ecosystems and follow MCP SDK conventions.

How to use Model-Context-Protocol Servers?

Clone the repository, navigate to the desired server directory, install dependencies (npm install for TypeScript/JavaScript servers, pip install for Python), set required environment variables (e.g., FIRECRAWL_API_KEY, DEEPSEEK_API_KEY), and start the server with npm start, node, or python as appropriate. Each server runs on stdio transport by default; the JSON Manager server also supports HTTP transport via the --port flag.

Key features of Model-Context-Protocol Servers

• Firecrawl integration for web scraping, crawling, and LLM extraction
• Specialized Leafly strain data extractor with regex and LLM strategies
• Codebase analysis with file navigation, search, and change monitoring
• DeepSeek R1 server for text generation, summarization, and streaming
• JSONPath-based querying, filtering, diffing, and result caching
• Multi-language support (TypeScript, Python, JavaScript)

Use cases of Model-Context-Protocol Servers

• Build AI agents that scrape and extract structured data from websites
• Analyze and navigate large codebases programmatically
• Generate, summarize, and stream text using DeepSeek AI models
• Query, filter, and compare JSON datasets with persistent caching

FAQ from Model-Context-Protocol Servers

What servers are included in this collection?

The collection includes four servers: Firecrawl Web Scraping (TypeScript, stdio), Codebase Analysis (Python, stdio), DeepSeek R1 (JavaScript, stdio), and JSON Manager (JavaScript, stdio/HTTP). Each is documented in the Server Index table.

What runtime dependencies are required?

Node.js for TypeScript and JavaScript servers, Python 3.12+ for the Codebase Analysis server. The Codebase Analysis server also requires the watchdog package for real-time file change monitoring.

How do I set up the Firecrawl Web Scraping server?

Navigate to the firecrawl-mcp-server directory, run npm install, copy .env.example to .env, add your FIRECRAWL_API_KEY, then run npm run build and npm start. Use the CLI command npm run scrape-leafly -- output.csv "strain list" to extract Leafly strain data directly.

Which servers require API keys?

The Firecrawl Web Scraping server requires a Firecrawl API key. The DeepSeek R1 server requires a DeepSeek API key, set in a .env file.

Does the JSON Manager server support HTTP transport?

Yes, the JSON Manager server can be started with --port=3000 to use HTTP transport in addition to stdio. All other servers use stdio only.