Code Analysis
This MCP server provides intelligent code analysis and semantic search capabilities for large codebases, built by Johann-Peter Hartmann using Python with FastMCP, PostgreSQL with pgvector, and OpenAI embeddings. It features TreeSitter-based code parsing, domain-driven analysis that extracts business entities and bounded contexts from code, incremental Git-based indexing, and advanced pattern detection including anti-pattern identification and architectural coupling analysis. The implementation supports natural language code search, hierarchical code explanations, dependency analysis, refactoring suggestions, and GitHub repository monitoring, making it valuable for understanding complex codebases, architectural reviews, and maintaining code quality across multiple repositories with up to 10M lines of code.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/johannhartmann/mcpcodeanalysis
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Code Analysis 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.