Happy slice of mcp pizzaMCP.pizza

contextplus

MCP.Pizza Chef: forloopcodes

This tool lets your AI assistant explore a large codebase the way an experienced engineer would — mapping out functions and classes, tracing where a piece of code is used elsewhere, and searching by meaning instead of exact keywords. It works inside Cursor, VS Code, and Windsurf, needs a short setup step, and requires an API key to power its search and chat features. Before your assistant changes any code, it automatically saves a backup so you can undo the change if something goes wrong.

Coding
Data

Use This MCP server To

Find any function in my codebase just by describing it See every place a piece of code is used before changing it Let my AI assistant edit code safely, with automatic backups Undo an AI-made code change with one click Browse my project by topic instead of file names Check my code for errors and dead code automatically Get a quick map of a big project's structure

README

Context+

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.

Video.Project.5.mp4

Tools

Discovery

Tool Description
get_context_tree Structural AST tree of a project with file headers and symbol ranges (line numbers for functions/classes/methods). Dynamic pruning shrinks output automatically.
get_file_skeleton Function signatures, class methods, and type definitions with line ranges, without reading full bodies. Shows the API surface.
semantic_code_search Search by meaning, not exact text. Uses embeddings over file headers/symbols and returns matched symbol definition lines.
semantic_identifier_search Identifier-level semantic retrieval for functions/classes/variables with ranked call sites and line numbers.
semantic_navigate Browse codebase by meaning using spectral clustering. Groups semantically related files into labeled clusters.

Analysis

Tool Description
get_blast_radius Trace every file and line where a symbol is imported or used. Prevents orphaned references.
run_static_analysis Run native linters and compilers to find unused variables, dead code, and type errors. Supports TypeScript, Python, Rust, Go.

contextplus FAQ

Can I use this to find code by describing what it does instead of remembering its exact name?
Yes — its meaning-based search lets you describe what you're looking for in plain words, and it finds the matching function, class, or file even if you don't recall its exact name.
Can I use this to safely let my AI assistant make changes to my code?
Yes — every proposed change is checked against a set of rules first, and a backup of your files is saved automatically before anything is written, so you can undo it later if needed.
Which apps does this work with?
It's built for Cursor, VS Code, and Windsurf, and it can be set up to work with other coding assistants that support the same connection method.
Do I need an account or API key to use it?
Yes — you'll need a key from an AI provider (for example, one that runs models locally through Ollama) to power the search and chat features, which you add to a small setup file.
Is this hard to set up?
It's a short copy-and-paste step — you add a few lines to a configuration file in your coding app, or use its built-in command to generate that file for you automatically.
Will this work on a very large codebase?
Yes — it's built specifically for large projects, automatically trimming what it shows you so you aren't overwhelmed with information.
Does it change my files without asking me first?
No — every proposed change goes through a validation step, and a backup is created beforehand so any change can be reversed.
Can I use this with Claude, ChatGPT, or Gemini?
It's designed to plug into Claude-based tools like Cursor and Windsurf, as well as VS Code; ChatGPT and Gemini are not currently listed among its supported apps.