# memory-mcp

> memory-mcp — marinski-memory-mcp. Use this tool when you need to access and search through past AI sessions or retrieve trusted semantic facts to inform your decisions. It solves problems of knowledge retention and recall, enabling more accurate and informed interactions. By providing a searchable archive and curated facts layer, memory-mcp takes in AI session data and outputs relevant information and insights.

Canonical page: https://skillsregistry.net/skills/marinski-memory-mcp  
JSON: https://api.skillsregistry.net/v1/skills/marinski-memory-mcp

## Description

Enables personal cross-tool memory by exposing a searchable episodic archive of AI sessions and a curated, high-trust semantic facts layer through MCP tools and resources.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/scg4qygx06)
- **Repository:** <https://github.com/Marinski/memory-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": "marinski-memory-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/marinski-memory-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/marinski-memory-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