# Roo Code Memory Bank

> Use this tool when you need to maintain persistent memory across sessions for complex projects, enabling AI assistants to keep track of context and decision history over time. It solves problems of lost context and incomplete project knowledge by providing a structured memory bank with standard markdown files. The tool accepts project context data as input and outputs a persistent memory bank with timestamped entries, making it ideal for developers and AI assistants working on long-term projects that require continuous knowledge management.

Canonical page: https://skillsregistry.net/skills/incomestreamsurfer-roo-code-memory-bank  
JSON: https://api.skillsregistry.net/v1/skills/incomestreamsurfer-roo-code-memory-bank

## Description

Roo Code Memory Bank MCP Server implements a file-based project context management system that enables AI assistants to maintain persistent memory across sessions. Built by IncomeStreamSurfer, it provides tools for initializing a structured memory bank with standard markdown files (productContext, activeContext, progress, decisionLog, systemPatterns), checking memory bank status, reading file contents, and appending timestamped entries to specific sections. The server uses Node.js with TypeScript and the MCP SDK to handle file operations asynchronously, making it particularly valuable for developers and AI assistants working on complex projects that require maintaining context and decision history over time.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/incomestreamsurfer-roo-code-memory-bank)
- **Repository:** <https://github.com/incomestreamsurfer/roo-code-memory-bank-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "incomestreamsurfer-roo-code-memory-bank"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/incomestreamsurfer-roo-code-memory-bank` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/incomestreamsurfer-roo-code-memory-bank/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt