What is a Memory Bank?
A structured repository of information stored as markdown files, including `product-context.md`, `active-context.md`, `progress.md`, `decision-log.md`, and `system-patterns.md`.
Memory Bank MCP With Remote SSH Support
@aakarsh-sasi
Basic information
About Memory Bank MCP With Remote SSH Support
MCP Server with Remote SSH support
Memory Bank MCP With Remote SSH Support config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"memory-bank-mcp-aakarsh-sasi": {
"command": "npx",
"args": [
"@aakarsh-sasi/memory-bank-mcp"
]
}
}
}Memory Bank MCP With Remote SSH Support tools
15Initialize a Memory Bank in the specified directory
Set a custom path for the Memory Bank
Debug the current MCP configuration
Read a file from the Memory Bank
Write to a Memory Bank file
List Memory Bank files
Check Memory Bank status
Migrate Memory Bank files from camelCase to kebab-case naming convention
Track progress and update Memory Bank files
Update the active context file
Log a decision in the decision log
Switches to a specific mode
Gets information about the current mode
Processes the Update Memory Bank (UMB) command
Completes the Update Memory Bank (UMB) process
Overview
What is Memory Bank MCP With Remote SSH Support?
A Model Context Protocol (MCP) server that enables AI assistants to store and retrieve structured information across sessions using Memory Banks. It now supports storing Memory Banks on a remote server via SSH.
How to use Memory Bank MCP With Remote SSH Support?
Install via npm (npm install @aakarsh-sasi/memory-bank-mcp) or run directly with npx (npx @aakarsh-sasi/memory-bank-mcp). Use command-line flags like --path, --folder, --mode, and --remote with --remote-user, --remote-host, --remote-path for remote mode. Configure as an MCP server in code editors like Cursor by specifying the npx command and arguments.
Key features of Memory Bank MCP With Remote SSH Support
- Initialize, find, and manage Memory Banks
- Read and write files in Memory Banks
- Track progress and log important decisions
- Maintain active context across sessions
- Support multiple modes (code, architect, ask, debug, test)
- Store Memory Banks on a remote server via SSH
Use cases of Memory Bank MCP With Remote SSH Support
- Maintain project context and progress across multiple AI assistant sessions
- Centralize Memory Banks on a remote server for shared access
- Persist Memory Bank data even if the local machine is wiped
- Log decisions with context and alternatives for project documentation
- Automatically switch AI behavior based on mode-specific
.clinerulesfiles
Frequently asked questions
Can I customize the Memory Bank folder name?
Yes, use the `--folder` option to set a custom folder name (e.g., `--folder custom-memory`). The Memory Bank is created at `<project_path>/<folder_name>`.
How do I set up the remote server mode?
Provide `--remote`, `--remote-user`, `--remote-host`, and `--remote-path` parameters. SSH key authentication is required; password authentication is not supported.
What modes are available and how do I switch?
Modes: `code`, `architect`, `ask`, `debug`, `test`. Start with `--mode <mode>` or use the `switch_mode` tool during a session. Mode-specific `.clinerules` files can also trigger automatic switching.
What are the SSH requirements for remote storage?
You need SSH access to the remote server, SSH key authentication set up, and sufficient permissions to create/modify files in the specified directory.
More Memory & Knowledge MCP servers
Neither MCP
stonianuaProject context your AI can query through MCP — with source evidence.
Groundwork
Rarefied-EarthGroundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
1
Memlord
MyrikLDMemlord is a remote MCP server available at https://app.memlord.com.
server-noonien - shared memory MCP
sequicoShared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
Tempreon
TempreonPerson-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Comments