contextplus

MCPOpen source

Semantic code intelligence MCP server with RAG, AST, spectral clustering, and memory graph for large codebases.

2kMIT

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.

Pros

+Combines RAG, AST, spectral clustering, and Obsidian-style linking for high accuracy
+Provides semantic search, code navigation, and blast radius analysis
+Includes memory graph with embeddings and relation traversal
+Supports multiple languages (TypeScript, Python, Rust, Go) for static analysis

Cons

−Requires external Ollama setup for embeddings and chat models
−May have a learning curve due to many tools and concepts
−Primarily designed for large-scale engineering, might be overkill for small projects

Target audience: Developers working on large codebases who need semantic code search, navigation, and AI-assisted code changes with high accuracy.