# mem9-guard-mcp

> Use this tool when you need to safeguard AI interactions with persistent memory, protecting against security threats like prompt injection and secret leakage. The mem9-guard-mcp server provides a secure interface to the mem9 backend, ensuring the integrity of AI agent interactions. Ideal for use cases requiring secure memory access, this tool takes in AI requests and returns protected memory outputs.

Canonical page: https://skillsregistry.net/skills/riku-kano-mem9-guard-mcp  
JSON: https://api.skillsregistry.net/v1/skills/riku-kano-mem9-guard-mcp

## Description

An MCP server that provides a guarded interface to the mem9 persistent memory backend, protecting AI agents against prompt injection, secret leakage, and memory poisoning.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dw0qvrewgo)
- **Repository:** <https://github.com/Riku-KANO/mem9-guard-mcp>

## 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": "riku-kano-mem9-guard-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/riku-kano-mem9-guard-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/riku-kano-mem9-guard-mcp/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