MCP server for semantic code search: index your codebase once, then search using natural language.
codebaxing 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 duysolo/codebaxing --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.
Codebaxing indexes your codebase and lets you search it using natural language, like asking a question. It understands the meaning behind your code, so you can find functions and logic even if you don't know the exact names. It works with AI editors like Claude and Cursor to help you navigate large projects quickly.
Codebaxing is an MCP (Model Context Protocol) server that provides semantic code search for your local codebase. It uses Tree-sitter to parse code into symbols, generates embeddings via a local or cloud model, and stores vectors in ChromaDB. Once indexed, you can search using natural language queries (e.g., "find authentication logic") and get relevant code snippets, even if the exact terms don't match. It supports multiple programming languages through Tree-sitter grammars. The tool offers a CLI for indexing and searching, and MCP tools for AI agents (search, stats, remember, recall, forget). Cloud embedding providers (Gemini, OpenAI, Voyage) are available for faster indexing. It integrates with Claude Desktop, Cursor, Windsurf, and other MCP-compatible editors.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 68 days ago.
54 GitHub stars indicate community interest.
1 open issues signal maintenance load.
MIT license detected.
Quickly find authentication logic in a large codebase without knowing exact function names.
Onboard new developers by letting them search the codebase in natural language.
Integrate with AI coding assistants to provide context-aware code retrieval.
Index multiple projects and search across them for reusable patterns.
Debug by searching for error handling patterns or specific API implementations.
Indexing sends code to cloud embedding providers if configured (Gemini, OpenAI, Voyage). Ensure compliance with data policies.
Local embedding runs entirely on your machine, but may be slow for large codebases.
54
Stars
6
Forks
1
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.
2 security/trust notes recorded.
Setup difficulty is 3/5.