Kiro Memory
This MCP server provides AI assistants with intelligent memory management and task tracking capabilities for software development projects, built by cbunting99 using Python with automatic project detection, semantic search via sentence-transformers, and SQLite-based persistence. The implementation features automatic memory classification and relationship building, context-aware task creation from conversation content, project-based organization with auto-detection from git repositories and project files, and comprehensive cleanup and optimization tools including duplicate detection and performance tracking. Serves developers needing persistent AI memory across coding sessions, teams requiring automated task management with priority inference and category classification, and projects where maintaining context and knowledge graphs enhances AI-assisted development workflows with semantic similarity matching and intelligent content organization.
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
- database
- Source
- PulseMCP
- Repository
- github.com/cbunting99/enhanced-mcp-memory
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Kiro Memory 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.