Memory BankSAFE
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@alioshr/memory-bank-mcp) [](https://www.npmjs.com/package/@allpepper/memory-bank-mcp) [](https://www.npmjs.com/package/@allpepper/memory-bank-mcp)
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Overview
The Memory Bank MCP Server transforms traditional file-based memory banks into a centralized service that:
- Provides remote access to memory bank files via MCP protocol
- Enables multi-project memory bank management
- Maintains consistent file structure and validation
- Ensures proper isolation between project memory banks
Features
- Multi-Project Support
- Project-specific directories
- File structure enforcement
- Path traversal prevention
- Project listing capabilities
- File listing per project
- Remote Accessibility
- Full MCP protocol implementation
- Type-safe operations
- Proper error handling
- Security through project isolation
- Core Operations
- Read/write/update memory bank files
- List available projects
- List files within projects
- Project existence validation
- Safe read-only operations
Installation
To install Memory Bank Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @alioshr/memory-bank-mcp --client claude
This will set up the MCP server configurati
ea5b178d92a3OBSERVED · 2026-09-26Connect
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 @allpepper/[email protected]
{
"mcpServers": {
"memory-bank-mcp": {
"command": "npx",
"args": [
"-y",
"@allpepper/[email protected]"
]
}
}
}Exposed tools (5)
3 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
list_project_files | read | List all files within a specific project |
list_projects | read | List all projects in the memory bank |
memory_bank_read | read | Read a memory bank file for a specific project |
memory_bank_update | write | Update an existing memory bank file for a specific project |
memory_bank_write | write | Create a new memory bank file for a specific project |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
.DS_Store
.DS_Store
import { File } from "../../domain/entities/index.js";import { Project } from "../../domain/entities/index.js";} from "../../../domain/usecases/index.js";
import { FileRepository, ProjectRepository } from "../../protocols/index.js";import { Project } from "../../../domain/entities/index.js";@modelcontextprotocol/sdk, fs-extra, @types/fs-extra, @types/node, @vitest/coverage-istanbul, @vitest/coverage-v8, @vitest/ui, shx
Gates applied: no_behavioural_pass.
ea5b178d92a3full audit observations/trust-audit/mcp-server/alioshr__memory-bank-1.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 |
|---|---|---|---|---|---|
| 2026-09-26 | ea5b178d92a3 | SAFE | B | 89 | first audit |
Questions
What is the Memory Bank MCP server?
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
What tools does Memory Bank expose?
5 in total: 3 read-only, 2 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?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
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 @allpepper/memory-bank-mcp at 0.2.1.
How current is this page?
The grade is for one exact copy of the source (ea5b178d92a3), read on 2026-09-26. The repository is watched and re-audited when it changes.