An MCP server that transforms large codebases into searchable, hierarchical feature graphs using RAG, AST, and spectral clustering.
contextplus is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view forloopcodes/contextplus --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Context+ is a tool that helps developers understand and navigate huge codebases. It uses advanced techniques like semantic search, code structure analysis, and clustering to find relevant code quickly. It also provides features like safe code editing with restore points and dependency tracing.
Context+ is an MCP (Model Context Protocol) server designed for developers working on large-scale engineering projects. It combines Retrieval-Augmented Generation (RAG), Tree-sitter AST parsing, Spectral Clustering, and Obsidian-style wikilinks to turn a massive codebase into a searchable, hierarchical feature graph. The server offers a suite of tools for discovery (e.g., semantic code search, AST tree navigation), analysis (blast radius, static analysis), code operations (safe commit proposals with restore points), version control (list/undo restore points), and memory/RAG (upsert memory nodes). It supports multiple programming languages and integrates with AI coding agents like Claude Code and Cursor. Context+ aims for 99% accuracy in code understanding and retrieval, making it suitable for complex, multi-file projects.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 36 days ago.
1916 GitHub stars indicate community interest.
7 open issues signal maintenance load.
MIT license detected.
Quickly understand the structure and dependencies of an unfamiliar codebase.
Find all usages and import locations of a specific function or class across the project.
Safely propose code changes with automatic restore points to revert if needed.
Navigate a codebase by semantic meaning rather than exact text matches.
Create and query a knowledge graph of code concepts and features using memory nodes.
The tool can modify files via propose_commit; ensure proper permissions and review changes.
Memory nodes may contain sensitive code or data; consider access controls.
Undo changes rely on shadow restore points; verify they are created before critical edits.
1,916
Stars
161
Forks
7
Issues
MIT
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
3 security/trust notes recorded.
Setup difficulty is 3/5.