CodeCortX
CodeCortX is a high-performance code analysis server built in Rust by Kenneth J. Sanchez that delivers deep code understanding capabilities across 15+ programming languages including Rust, Python, TypeScript, Java, Go, and C++. Using Tree-sitter for parsing and BM25 for semantic search, it offers real-time symbol extraction, file watching with automatic re-indexing, and memory-efficient caching with LRU eviction. The implementation prioritizes performance with concurrent processing, smart memory management, and sub-millisecond symbol lookups, making it valuable for understanding large codebases, providing intelligent code suggestions, performing cross-language analysis, and assisting with code navigation and refactoring tasks.
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
- productivity
- Source
- PulseMCP
- Repository
- github.com/kensave/roberto-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve CodeCortX 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.