Memory BankSAFE
Memory Bank is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains a set of interconnected Markdown documents that capture different aspects of project knowledge, from high-level goals to technical details and day-to-day progress.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Memory Bank MCP
Structured project knowledge management for LLMs via Model Context Protocol (MCP)
Note: This is not a traditional Node.js application. Memory Bank MCP is an MCP server—a component in the Model Context Protocol ecosystem. It exposes project knowledge to LLM-powered agents and tools using a standardized protocol, enabling seamless integration with AI clients (e.g., Claude Desktop, IDEs, or custom LLM agents).
What is Model Context Protocol (MCP)?
MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI: it provides a universal way to connect AI models to data sources and tools, both locally and remotely. MCP enables:
- Plug-and-play integrations between LLMs, data, and tools
- Switching between LLM providers with minimal friction
- Secure, modular architecture for building AI workflows
Learn more: MCP Introduction
About Memory Bank MCP
Memory Bank MCP is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains interconnected Markdown documents capturing all aspects of project knowledge, from high-level goals to technical details and daily progress. It is designed to be accessed by MCP-compatible clients and LLM agents.
Features
- AI-Generated Documentation: Uses Gemini API to generate and update project documentation
- Structured Knowledge System: Maintains six core document types in a hie
171b2d00bd61OBSERVED · 2026-10-07Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add memory-bank-mcp --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"memory-bank-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (5)
3 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
create_cursor_rules | write | |
export_memory_bank | read | |
initialize_memory_bank | read | |
query_memory_bank | read | |
update_document | write |
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 | PASS |
| 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
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.byterules
@google/generative-ai, @modelcontextprotocol/sdk, dotenv, zod, fs-extra, @types/fs-extra, @types/node, ts-node
Gates applied: no_behavioural_pass, no_license.
171b2d00bd61full audit observations/trust-audit/mcp-server/tuncer-byte__memory-bank-6.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 171b2d00bd61 | SAFE | B | 89 | first audit |
Questions
What is the Memory Bank MCP server?
Memory Bank is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains a set of interconnected Markdown documents that capture different aspects of project knowledge, from high-level goals to technical details and day-to-day progress.
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?
It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Memory Bank run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as memory-bank-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (171b2d00bd61), read on 2026-10-07. The repository is watched and re-audited when it changes.