pulsemcp Safe content atomic mcp-remote

Memory Bank

Memory Bank MCP server by Nick Cao that implements a structured development workflow system with five distinct operational modes: VAN for project initialization and complexity assessment, PLAN for creating detailed implementation strategies, CREATIVE for design and architecture work, IMPLEMENT for execution based on plans, and REFLECT+ARCHIVE for project completion and documentation. The implementation uses a file-based storage system that maintains persistent state across workflow phases in a `.memory_bank` directory, with each mode designed to handle different complexity levels from simple tasks to complex multi-phase projects. Built with TypeScript and the MCP SDK, it serves developers who want to maintain structured project context and follow systematic development workflows, particularly useful for managing complex implementations that require careful planning, creative problem-solving, and thorough documentation throughout the development lifecycle.

Cognium trust score

50%

Tier

Unverified

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: productivity
Source: PulseMCP
Repository: github.com/nicavcrm/memory-bank-mcp
Author type: human
Updated: 2026-04-29

View source Find related skills

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

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"