Graphify-Labs/graphify
Graphify transforms codebases, documentation, and other files into queryable knowledge graphs, enhancing developer productivity with local AST parsing and detailed edge explanations.
Awesome MCP › Software Development
The project "wcgw" is an MCP (Model Context Protocol) server designed to integrate shell and coding tools, enabling AI-assisted coding, building, and running tasks on local machines through the Claude desktop app and other MCP clients. It empowers chat applications to interact with the local development environment by providing tightly integrated shell and code editing capabilities. The server supports various advanced features such as creating, executing, and iterating code with continuous compiler checks until errors are resolved, and handling large file edits incrementally to avoid token limit issues. Syntax checking on file edits is implemented to provide feedback to the AI for corrections, enhancing code quality and reducing errors. The project emphasizes safety and control by requiring the AI to read a file at least once before editing it, preventing accidental overwrites. It also manages file context efficiently by chunking large files based on token length and selecting important files during initialization using .gitignore and statistical methods. Shell command execution is optimized by allowing only one command at a time and maintaining a single shell instance, with mechanisms to keep the AI aware of the current working directory and command status. Additional features include saving repository context in a single file for task checkpointing and knowledge transfer, multiple operational modes (architect, code-writer, and full wcgw mode) for different stages of development, and the ability to attach to the terminal session used by the AI for real-time interaction. The server automatically loads project-specific and global CLAUDE.md instruction files during initialization to guide AI behavior. Use cases range from solving coding problems, running tests, and fixing issues, to managing complex workflows like creating branches, running multiple servers, and building and testing applications across different environments. The project supports integration with Claude and other MCP clients on Mac, Linux, and Windows (via WSL), with detailed setup instructions provided. Overall, wcgw is a powerful tool for enhancing AI-assisted software development workflows by bridging chat-based AI models with local coding and shell environments through the MCP framework.
https://github.com/rusiaaman/wcgw
Graphify transforms codebases, documentation, and other files into queryable knowledge graphs, enhancing developer productivity with local AST parsing and detailed edge explanations.
Context7 MCP Server is an MCP server that delivers up-to-date, version-specific code documentation and examples to enhance LLMs and AI code editors, ensuring accurate and current code generation.
High-performance Model Context Protocol (MCP) server that indexes codebases into a persistent knowledge graph for AI coding agents, supporting 158 languages, lightning-fast queries, and various dev...
GitHub MCP Server is an official Model Context Protocol server that integrates with GitHub APIs to enable advanced automation and AI-powered interactions with GitHub repositories and workflows.
Code-review-graph is a local-first code intelligence solution that builds a persistent structural map of your codebase to provide precise context to AI coding tools, significantly reducing token us...
Serena is a free and open-source coding agent toolkit that uses the Model Context Protocol to enable LLMs to autonomously perform semantic code retrieval and editing with IDE-like precision on complex codebases.
Claude Task Master is an AI-powered task management system designed for AI-driven development that integrates seamlessly with various editors via the Model Control Protocol (MCP).
Context Mode is an MCP server designed to optimize context window usage for AI coding agents by sandboxing tool output, tracking session continuity with SQLite, and promoting LLMs as code generator...