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
tirth8205/code-review-graph
Code-review-graph is an innovative tool designed to optimize the performance and cost-efficiency of AI coding assistants by addressing the common issue of excessive token consumption during code reviews. It operates by creating a local-first, persistent knowledge graph of a software repository, leveraging Tree-sitter to parse the Abstract Syntax Tree (AST) of the codebase. This graph stores nodes representing functions, classes, and imports, and edges indicating calls, inheritance, and test coverage. The core functionality revolves around providing AI assistants with a minimal, yet comprehensive, context via the Model Context Protocol (MCP). When a code review or similar task is initiated, the tool performs a "blast radius" analysis. It traces all callers, dependents, and tests potentially affected by a change, allowing the AI to focus only on relevant files. This dramatically reduces the amount of code the AI needs to process, as demonstrated by benchmarked token reductions ranging from 38x to 528x across real repositories. The system supports incremental updates, re-indexing large projects in under two seconds by diffing changed files and re-parsing only what's necessary. This makes it highly efficient for continuous integration and large monorepo environments, where it can exclude tens of thousands of irrelevant files from review context. Code-review-graph offers broad language coverage, including various programming languages, Jupyter notebooks, and configuration files, ensuring versatility across diverse development stacks. Installation is streamlined, auto-detecting and configuring support for numerous AI coding platforms and editors, including Codex, Claude Code, Cursor, and GitHub Copilot, by generating appropriate MCP configurations and platform-native hooks.
https://github.com/tirth8205/code-review-graph
Also in Software Development
upstash/context7
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.
DeusData/codebase-memory-mcp
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/github-mcp-server
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.
oraios/serena
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.
eyaltoledano/claude-task-master
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).
mksglu/context-mode
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...
comet-ml/opik
Opik is an open-source platform for debugging, evaluating, and monitoring large language model applications with comprehensive tracing, automated evaluations, and production-ready dashboards.