Memory Bank
This MCP server provides persistent project context management through a structured "Memory Bank" system that maintains five core markdown files tracking project goals, current status, progress, decisions, and patterns. Built using TypeScript with the MCP SDK and Zod validation, it offers tools for initializing memory bank directories with templated files, reading all context files to provide AI assistants with comprehensive project understanding, and generating detailed update instructions based on change types (architecture, feature, bugfix, refactor, decision, progress). The implementation includes automatic timestamp tracking, file relationship management, and specific workflow guidance for maintaining consistency across all context files, making it valuable for AI-assisted development workflows that require persistent project memory, long-term context preservation across coding sessions, and structured documentation of architectural decisions and development progress.
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
- file-system
- Source
- PulseMCP
- Repository
- github.com/hoppo-chan/memory-bank-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Memory Bank 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.