
Auto Dev Next
unit-mesh/auto-dev-next
The auto-dev-next project, to be released before April 1, 2026.

adi2355/Model-Context-Protocol-servers
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.
See repository
Setup steps are in the repository README.
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).
firecrawl_scrape
Scrape a single page with format selection (markdown, HTML, screenshots), custom actions, and content filtering
firecrawl_map
Discover all URLs on a website and generate a site map
firecrawl_crawl
Recursively crawl a website with depth and page limits
firecrawl_batch_scrape
Scrape multiple URLs concurrently with queue-based processing
firecrawl_check_batch_status
Poll the status of an in-progress batch scrape job
firecrawl_check_crawl_status
Poll the status of an in-progress crawl job
firecrawl_search
Search the web and return scraped content from results
firecrawl_extract
LLM-powered structured data extraction using a caller-defined JSON schema
firecrawl_deep_research
Multi-step research workflow that scrapes, synthesizes, and reports on a topic
firecrawl_leafly_strain
Extract standardized cannabis strain data (cannabinoids, terpenes, effects, flavors, interactions)
search_function
Find function definitions across Python, JavaScript, and TypeScript files
search_code
Full-text search across all code files in a directory tree
get_project_structure
Generate a tree-view representation of the project directory
analyze_dependencies
Parse and analyze project dependency manifests
find_components
Discover React and React Native component definitions
deepseek_r1
Generate text using the DeepSeek Reasoner model (optimized for complex reasoning)
deepseek_summarize
Condense text into a summary
deepseek_stream
Stream text generation with chunked output
deepseek_multi
Generate text using a caller-specified DeepSeek model variant
deepseek_document
Process documents: summarize, extract entities, or analyze sentiment
query
Query JSON data using JSONPath expressions with array operations
filter
Filter JSON arrays by field conditions (equality, range, pattern matching)
save_query
Persist query results to disk for later retrieval
compare_json
Diff two JSON datasets and report structural/value differences
Details on this page are taken from the project's README. Open README

unit-mesh/auto-dev-next
The auto-dev-next project, to be released before April 1, 2026.

sub-arjun/OMNI-Sales
A sales management control protocol server for the OMNI-Sales project.

terraform-check-001/hello-world-test-5
Project created via a custom MCP server

yuvalsolaz/geo-mcp-server
Geographic multi-protocol computing platform service.

adrian-d-hidalgo/nestjs-mcp-server
NestJS MCP Server is a modular library for building Model Context Protocol (MCP) servers using NestJS. It provides decorators, modules, and integration patterns to expose MCP resources, tools, and prompts in a scalable, maintainable way.

uukelele-scratch/scratchattach-mcp
An MCP server that allows any agent to connect to Scratch.