Index and search your codebase using WASM-powered tree-sitter parsing. For developers who need fast, cross-platform code navigation and context extraction without external dependencies.
io.github.Jhackman2019/codebase-context-mcp
Local install
STDIO
No auth required
How models use it and what it is built for.
Index and search your codebase using WASM-powered tree-sitter parsing. For developers who need fast, cross-platform code navigation and context extraction without external dependencies.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Jhackman2019 Codebase Context.
Paste any of these into Agent Studio after connecting Jhackman2019 Codebase Context.
Common questions about connecting and running Jhackman2019 Codebase Context.
What platforms does codebase-context-mcp support?
The server runs on both ARM64 and x86_64 architectures, making it compatible with modern development machines and CI/CD environments. It uses WASM tree-sitter for efficient, cross-platform code parsing.
How do I install and run this MCP server?
Install via npm with `npx codebase-context-mcp@1.0.1`. The server communicates over stdio, so configure your MCP client to spawn the process and pipe input/output accordingly.
Does this require external language servers or dependencies?
No. The server uses WASM tree-sitter for parsing, which is bundled and runs locally. This means no external LSP servers or network calls are needed for indexing and search.
What languages does tree-sitter support for parsing?
Tree-sitter supports dozens of languages including JavaScript, TypeScript, Python, Go, Rust, Java, and more. Check the tree-sitter documentation for the full list of available language grammars.
Can I use this for large codebases?
Yes. WASM tree-sitter is designed for performance and can handle large projects efficiently. Indexing happens locally on your machine, so speed depends on your hardware and codebase size.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio