model-context-protocol-servers

Overview

This repository contains a collection of purpose-built Model Context Protocol servers, each designed around a specific capability: web scraping and structured data extraction, codebase navigation and analysis, LLM-powered text generation, and JSON querying. Every server exposes its functionality as MCP tools and resources, making them composable building blocks for AI agent workflows.

The servers span two language ecosystems — TypeScript for the Firecrawl integration and DeepSeek/JSON servers, Python for the codebase analysis server — and follow the MCP SDK conventions for tool definitions, resource URIs, and transport configuration (stdio and HTTP).

Technology Stack

Languages

MCP Framework

Web Scraping

AI Integration

Data & Querying

Runtime

Tooling

Server Index

Firecrawl Web Scraping Server

A comprehensive MCP server built on the Firecrawl platform for web scraping, content extraction, and structured data collection. Extends the base Firecrawl capabilities with a specialized cannabis strain data extraction pipeline that collects 66 standardized data points per strain from Leafly.com using dual extraction strategies: regex-based pattern matching and LLM-powered schema extraction.

Tools

Strain Data Extraction Pipeline

The Leafly strain extractor is the most specialized component in this collection. It implements two complementary extraction strategies against the same data source:

Regex-based extraction parses raw HTML/markdown content with pattern-matching rules for cannabinoid percentages, terpene profiles, effect ratings, and flavor descriptors. This approach is deterministic and fast, but brittle against layout changes.

LLM-powered extraction uses Firecrawl's `extract` endpoint to send page content to an LLM with a structured JSON schema. This approach handles unstructured text, formatting variations, and missing data more gracefully, at the cost of API latency and token usage.

Both strategies normalize output to a consistent schema covering:

Normalization methodology: lab-tested data is prioritized. When exact values are unavailable, standardized normalization is applied (dominant terpene = 0.008, second = 0.005, third = 0.003). Effects and flavors are normalized to a 0.0–1.0 scale.

Quick Start

cd firecrawl-mcp-server
npm install
cp .env.example .env          # Add your FIRECRAWL_API_KEY
npm run build
npm start                     # Start the MCP server (stdio transport)

# CLI: extract strain data directly
npm run scrape-leafly -- output.csv "Blue Dream,OG Kush,Sour Diesel"

Codebase Analysis Server

A Python MCP server for navigating and analyzing codebases. Provides file system access, text search, function discovery, dependency analysis, and real-time file change monitoring via watchdog. Built with the Python MCP SDK's `FastMCP` framework.

Tools

Resources

Quick Start

cd Model-Context-Protocol-servers
pip install "mcp[cli]" watchdog
python code_server.py

DeepSeek R1 Server

An MCP server that integrates with DeepSeek AI models for text generation, summarization, streaming output, and document processing. Supports multiple DeepSeek models (Reasoner, Chat, Coder) through the OpenAI-compatible API. Includes an in-memory response cache and file persistence for generated outputs.

Tools

Resources

Supported Models

Quick Start

cd Model-Context-Protocol-servers
echo "DEEPSEEK_API_KEY=your_key_here" > .env
npm install @modelcontextprotocol/sdk openai dotenv
node deepseek.py                # Starts on stdio transport

JSON Manager Server

An MCP server for querying, filtering, comparing, and caching JSON data. Uses JSONPath expressions for traversal, supports advanced filtering with string, numeric, and date operations, and provides persistent query storage. Supports both stdio and HTTP transports.

Tools

Resources

Quick Start

cd Model-Context-Protocol-servers
npm install @modelcontextprotocol/sdk node-fetch jsonpath
node json.py                          # stdio transport (default)
node json.py --port=3000              # HTTP transport

Project Structure

.
├── firecrawl-mcp-server/                  # TypeScript — Firecrawl + Leafly MCP server
│   ├── src/
│   │   ├── index.ts                       # MCP server entry point (10 tools)
│   │   ├── leafly-scraper.ts              # Strain data extraction engine
│   │   ├── leafly-scraper-cli.ts          # CLI interface for direct scraping
│   │   └── index.test.ts                  # Jest test suite
│   ├── leafly-extract-data/               # Extracted strain datasets (batches + individual)
│   ├── leafly-analysis/                   # Raw HTML analysis of strain pages
│   ├── extract-test-output/               # Sample extraction results
│   ├── Dockerfile                         # Container build
│   ├── package.json
│   └── tsconfig.json
│
├── Model-Context-Protocol-servers/        # Python + JavaScript MCP servers
│   ├── code_server.py                     # Codebase analysis server (Python, FastMCP)
│   ├── deepseek.py                        # DeepSeek R1 server (JavaScript, FastMCP)
│   ├── json.py                            # JSON manager server (JavaScript, FastMCP)
│   ├── main.py                            # Python entry point
│   └── pyproject.toml                     # Python project configuration
│
├── terminal-top-panel.svg                 # README header graphic
├── terminal-bottom-panel.svg              # README footer graphic
└── README.md

Getting Started

Prerequisites

• Node.js 18+ for the Firecrawl, DeepSeek, and JSON servers
• Python 3.12+ for the codebase analysis server
• Firecrawl API key for the web scraping server (obtain from firecrawl.dev)
• DeepSeek API key for the DeepSeek R1 server (obtain from deepseek.com)

Installation

# Clone the repository
git clone https://github.com/adi2355/MCP-Server-Collection.git
cd MCP-Server-Collection

# Firecrawl server
cd firecrawl-mcp-server && npm install && npm run build && cd ..

# Python codebase server
cd Model-Context-Protocol-servers && pip install "mcp[cli]" watchdog && cd ..

Environment Variables

License

MIT License