Memory BankBLOCK
MCP Server with Remote SSH support
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@aakarsh-sasi/memory-bank-mcp) [](https://opensource.org/licenses/MIT) [](https://github.com/movibe/memory-bank-mcp/actions/workflows/test.yml) [](https://smithery.ai/server/@aakarsh-sasi/memory-bank-mcp)
A Model Context Protocol (MCP) server for managing Memory Banks, allowing AI assistants to store and retrieve information across sessions. Now with remote server support!
Overview 📋
Memory Bank Server provides a set of tools and resources for AI assistants to interact with Memory Banks. Memory Banks are structured repositories of information that help maintain context and track progress across multiple sessions.
Features ✨
- Memory Bank Management: Initialize, find, and manage Memory Banks
- File Operations: Read and write files in Memory Banks
- Progress Tracking: Track progress and update Memory Bank files
- Decision Logging: Log important decisions with context and alternatives
- Active Context Management: Maintain and update active context information
- Mode Support: Detect and use .clinerules files for mode-specific behavior
- UMB Command: Update Memory Bank files temporarily with the UMB command
- Robust Error Handling: Gracefully handle errors and continue operation when possible
- Status Prefix System: Immediate visibility into Memory Bank operational state
- Remote Server Support: Store Memory Banks on a remote server us
d9be4d1ed2bfOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add memory-bank-mcp -- npx -y @aakarsh-sasi/[email protected]
{
"mcpServers": {
"memory-bank-mcp": {
"command": "npx",
"args": [
"-y",
"@aakarsh-sasi/[email protected]"
]
}
}
}Exposed tools (15)
9 read · 6 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
complete_umb | write | Completes the Update Memory Bank (UMB) process |
debug_mcp_config | read | Debug the current MCP configuration |
get_current_mode | read | Gets information about the current mode |
get_memory_bank_status | read | Check Memory Bank status |
initialize_memory_bank | read | Initialize a Memory Bank in the specified directory |
list_memory_bank_files | read | List Memory Bank files |
log_decision | read | Log a decision in the decision log |
migrate_file_naming | read | Migrate Memory Bank files from camelCase to kebab-case naming convention |
process_umb_command | write | Processes the Update Memory Bank (UMB) command |
read_memory_bank_file | read | Read a file from the Memory Bank |
set_memory_bank_path | write | Set a custom path for the Memory Bank |
switch_mode | read | Switches to a specific mode |
track_progress | write | Track progress and update Memory Bank files |
update_active_context | write | Update the active context file |
write_memory_bank_file | write | Write to a Memory Bank file |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (21)
const rule = yaml.load(content) as ClineruleBase;
--ssh-key, -k <path> Path to SSH private key (default: ~/.ssh/your_ssh_key)
let sshKey = options.sshKey || `${homeDir}/.ssh/your_ssh_key`;.clinerules-architect
.clinerules-ask
.clinerules-code
.clinerules-debug
.clinerules-test
import { MemoryBankManager } from '../../core/MemoryBankManager.js';import { handleSetMemoryBankPath, handleInitializeMemoryBank } from '../../server/tools/CoreTools.js';import { MemoryBankServer } from '../../server/MemoryBankServer.js';import { MemoryBankManager } from '../../core/MemoryBankManager.js';import { MemoryBankManager } from '../../core/MemoryBankManager.js';@types/node, fs-extra, path, @types/bun, @types/fs-extra, standard-version, typescript
cat ~/.ssh/id_ed25519.pub # copy the output
require('dotenv').config(); // Load API key from .env fileload_dotenv() # load environment variables from .env
cat ~/.ssh/id_ed25519.pub # or id_rsa.pub
cat ~/.ssh/id_ed25519.pub | pbcopy
curl -fsSL https://bun.sh/install | bash
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
d9be4d1ed2bffull audit observations/trust-audit/mcp-server/aakarsh-sasi__memory-bank.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | d9be4d1ed2bf | BLOCK | D | 69 | first audit |
Questions
What is the Memory Bank MCP server?
MCP Server with Remote SSH support
What tools does Memory Bank expose?
15 in total: 9 read-only, 6 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Memory Bank safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Memory Bank need?
No credential environment variables were found in its source, so it appears to need none.
How does Memory Bank run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @aakarsh-sasi/memory-bank-mcp at 1.1.4.
How current is this page?
The grade is for one exact copy of the source (d9be4d1ed2bf), read on 2026-10-08. The repository is watched and re-audited when it changes.