Codebase Index
Codebase indexing server that integrates Qdrant Cloud vector storage with Google Gemini embedding models (text-embedding-004 or gemini-embedding-001) to enable natural language code search. Features incremental indexing with file change detection to reduce reprocessing time by 90%, intelligent code chunking by language-specific patterns (functions, classes) across Python, TypeScript, JavaScript, Java, Go, Rust, and Dart, and real-time file watching for automatic updates. Includes daily quota management to respect API limits, complexity scoring for code context, and 2D/3D vector visualization capabilities. Useful for understanding large projects, finding specific implementations, code review assistance, and developer onboarding.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/ngotaico/mcp-codebase-index
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Codebase Index from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.