# Marvis Working Memory MCP

> Marvis Working Memory MCP — fangsylar-pixel-marvis-working-memory-mcp. Use this tool when you need to enable AI agents to retain and recall information across tasks, solving problems of knowledge loss and inconsistent decision-making. It provides a local persistent working memory, accepting JSON inputs and outputs, to store and retrieve rules, preferences, and project state. Ideal for use cases requiring AI agents to learn from experiences and adapt to new information over time.

Canonical page: https://skillsregistry.net/skills/fangsylar-pixel-marvis-working-memory-mcp  
JSON: https://api.skillsregistry.net/v1/skills/fangsylar-pixel-marvis-working-memory-mcp

## Description

Provides local persistent working memory for AI agents, allowing them to load rules, preferences, and project state before tasks and save validated experiences after successful completion. Works with stdio MCP clients via a local JSON file.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-04

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xxsmd5tg1p)
- **Repository:** <https://github.com/fangsylar-pixel/marvis-working-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": "fangsylar-pixel-marvis-working-memory-mcp"
    }
  }
}
```

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