mcp-codebase-index and code-memory
These are complements: one provides precise structural navigation through AST-based queries while the other enables fuzzy semantic search through vector embeddings, addressing different code discovery needs within the same indexing workflow.
About mcp-codebase-index
MikeRecognex/mcp-codebase-index
17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
This tool helps software developers quickly understand and navigate large codebases. It takes your source code files (Python, TypeScript, Go, Rust, C#, Markdown) and creates a detailed map of functions, classes, imports, and dependencies. The output is a structured index that AI assistants like Claude Code can use to answer questions about the code, find specific elements, and trace dependencies much faster than reading files directly. It's designed for developers working on complex software projects.
About code-memory
kapillamba4/code-memory
MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.
This tool helps software developers quickly find relevant information within their large codebases without manually sifting through files. It takes your code and documentation as input, processes it locally, and then allows you to semantically search for code definitions, architectural patterns, or even Git history. The output is precise code snippets, documentation sections, or commit messages relevant to your query, helping you understand, debug, or extend existing projects more efficiently.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work