AI Code Review
Provides AI coding assistants with local static analysis capabilities across Python, JavaScript, TypeScript, Java, Go, Rust, C++, and other languages. Exposes three tools: `analyze_file` for per-file quality scoring, complexity metrics, and line statistics; `review_diff` for inspecting uncommitted git changes and detecting issues like hardcoded credentials; and `check_project` for whole-codebase quality overviews. Python files receive AST-based analysis; other languages receive general quality checks. Grades range from A to D based on weighted scoring of errors, warnings, and informational findings.
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 2026-09-03.
Scan details: Circle-IR · 2026-09-03 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Repository
- github.com/alanniew/code-review-mcp
- Author type
- human
- Last scanned
- 2026-09-03
- Updated
- 2026-09-03
Use via MCP
Resolve AI Code Review 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.