# Agent Memory MCP

> Use this tool when you need to manage and store agent memories, enabling efficient creation, retrieval, and modification of memories across global or repository scopes. It solves problems related to knowledge retention and information sharing between agents, providing a centralized server for memory management. The Agent Memory MCP accepts memory data as input and outputs stored memories, lists, or updated records, making it ideal for use cases requiring persistent agent knowledge storage.

Canonical page: https://skillsregistry.net/skills/msr806-agent-memory-mcp  
JSON: https://api.skillsregistry.net/v1/skills/msr806-agent-memory-mcp

## Description

MCP server for agent-maintained memories, allowing creation, reading, updating, deletion, and listing of memories with global or repo scopes.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kvam8jqt80)
- **Repository:** <https://github.com/MSR806/agent-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": "msr806-agent-memory-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/msr806-agent-memory-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/msr806-agent-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