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
Sourcerer MCP is a Go server that gives coding agents semantic search over a codebase, with token economy as the explicit design goal: instead of reading entire files into the context window, an agent searches conceptually and receives only the functions, classes or chunks that match. Indexing has two stages. Tree-sitter parses each source file and splits it along syntactic boundaries, so a chunk is a whole function or class rather than an arbitrary line range. Each chunk is then embedded and stored in a local vector database under a .sourcerer directory in the workspace, which the README asks users to add to .gitignore. Search queries are embedded the same way and matched against that index, and navigation tools let the agent jump from a result to related code. The workspace must be a git repository, and .gitignore is respected so generated and vendored files stay out of the index. Embeddings currently require an OpenAI API key, with local embedding support listed as planned. Installation is go install or a Homebrew tap, and the README gives both a claude mcp add command and a plain mcp.json block. The audience is developers running coding agents on repositories large enough that reading files exhaustively is slow and expensive.
https://github.com/st3v3nmw/sourcerer-mcp
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...