forloopcodes/contextplus

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1976 stars · 165 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Context+ is an MCP server that gives AI coding agents semantic understanding of large codebases by combining RAG embeddings, Tree-sitter AST parsing, and spectral clustering into a searchable hierarchical feature graph. It exposes tools for semantic code search, blast-radius analysis, static analysis, and validated code writes via stdio to IDEs like Claude Code, Cursor, and VS Code.

Use cases

• give my AI coding agent accurate context about a large codebase
• search code by meaning instead of exact text
• find every file and line affected by changing a function
• map features to code files in a massive repository
• reduce token usage when agents explore a codebase
• run semantic navigation over a monorepo with an MCP server

When to choose

• you use MCP-compatible IDEs or agents (Claude Code, Cursor, Windsurf, VS Code) on large codebases
• you want semantic retrieval plus AST-accurate symbol and line-level results
• you can run Ollama locally or via cloud for embeddings and chat models

When to avoid

• you need a standalone code search tool without an MCP client
• you cannot run Ollama or provide an Ollama API key
• your project is small enough that plain grep or IDE search suffices

Facets

service · maturity active

mcp rag search-engine parser static-site-generator developer-tools large-language-models cli cross-platform mcp-server code-search tree-sitter spectral-clustering semantic-code-navigation ollama codebase-understanding typescript ai-agents search nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="forloopcodes/contextplus")