CodeFlow
This CodeFlow MCP server provides semantic code analysis and search capabilities for Python codebases through AST extraction, call graph generation, and vector embeddings via ChromaDB and sentence-transformers. Built with cognitive load optimization principles, it extracts rich metadata including cyclomatic complexity, decorators, exception handling patterns, and external dependencies, then builds persistent vector stores for rapid semantic search and call graph visualization through Mermaid diagrams with LLM-optimized output modes. The implementation features real-time file watching for incremental updates, entry point detection using multiple heuristics, and comprehensive tools for function metadata retrieval, making it valuable for developers and AI assistants who need to understand complex codebases, perform semantic code search, generate architectural documentation, and navigate large Python projects efficiently.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/mrorigo/code-flow-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve CodeFlow 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.