MikeRecognex/mcp-codebase-index
17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
Platform-specific configuration:
{
"mcpServers": {
"mcp-codebase-index": {
"command": "npx",
"args": [
"-y",
"mcp-codebase-index"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<!-- mcp-name: io.github.MikeRecognex/mcp-codebase-index -->
[](https://pypi.org/project/mcp-codebase-index/) [](https://github.com/MikeRecognex/mcp-codebase-index/actions/workflows/ci.yml) [](https://www.python.org/downloads/) [](https://www.gnu.org/licenses/agpl-3.0) [](https://modelcontextprotocol.io) []()
A structural codebase indexer with an MCP server for AI-assisted development. Zero runtime dependencies — uses Python's ast module for Python analysis and regex-based parsing for TypeScript/JS, Go, Rust, and C#. Requires Python 3.11+.
Indexes codebases by parsing source files into structural metadata -- functions, classes, imports, dependency graphs, and cross-file call chains -- then exposes 18 query tools via the Model Context Protocol, enabling Claude Code and other MCP clients to navigate codebases efficiently without reading entire files.
Automatic incremental re-indexing: In git repositories, the index stays up to date automatically. Before every query, the server checks git diff and git status (~1-2ms). If files changed, only those files are re-parsed and the dependency graph is rebuilt. No need to manually call reindex after edits, branch switches, or pulls.
Persistent disk cache: The index is saved to a pickle cache file (.codebase-index-cache.pkl) after every build. On subsequent server starts, the cache is loaded and validated against the current git HEAD — if the ref matches, startup is instant. If a small number of
Loading reviews...