mcp-codebase-index and CodeMCP
About mcp-codebase-index
MikeRecognex/mcp-codebase-index
17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
Implements a streaming AST and regex-based parser with automatic git-aware incremental indexing—only changed files are reparsed, with built-in persistent caching via pickle that detects git HEAD mismatches and enables instant cold starts. Exposes Python, TypeScript, Go, Rust, and C# structural analysis (functions, classes, imports, callchains) as 18 MCP tools compatible with Claude Code and OpenClaw, eliminating file-reading overhead in large codebases.
About CodeMCP
SimplyLiz/CodeMCP
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping
Leverages SCIP-based semantic indexing to build cross-file call graphs and dependency analysis—currently supporting Go (Tier 1), TypeScript/JavaScript/Python (Tier 2), and other languages with varying feature completeness. The tool operates through three interfaces: MCP (Model Context Protocol) for seamless integration with Claude and other AI assistants, a CLI for direct terminal queries, and an HTTP API for CI/CD pipelines and custom tooling. Features include semantic call graph navigation, blast radius calculation with risk scoring, dead code detection, ownership tracking via CODEOWNERS analysis, and automated secret scanning with 26 patterns—all designed to reduce token usage by 83% through smart preset loading.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work