Codebase Insight
MCP Codebase Insight provides AI assistants with deep analysis capabilities for software repositories, enabling pattern detection, architecture understanding, and knowledge management. Built around a FastAPI server with Qdrant vector database integration, it features core modules for code analysis, ADR (Architecture Decision Record) management, documentation handling, and debugging assistance. The implementation includes a comprehensive caching system for performance optimization, health monitoring for reliability, and a structured knowledge base that stores code patterns with similarity search. Particularly valuable for developers seeking to understand complex codebases, document architectural decisions, or debug challenging issues without leaving their AI assistant conversation.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/tosin2013/mcp-codebase-insight
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Codebase Insight 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.