# CoreMemory-MCP

> Use this tool when you need to enable AI agents to retain information over time, solving problems of knowledge loss between sessions and facilitating continuous learning. CoreMemory-MCP provides a persistent storage service, accepting input data from MCP-compatible agents and outputting recalled information as needed. This tool is ideal for use cases requiring long-term memory retention, such as conversational dialogue systems or personalized recommendation engines.

Canonical page: https://skillsregistry.net/skills/michaelfeng-corememory-mcp  
JSON: https://api.skillsregistry.net/v1/skills/michaelfeng-corememory-mcp

## Description

Provides a local, persistent long-term memory service for MCP-compatible AI agents, enabling them to store, search, and recall information across sessions.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nbs076a17j)
- **Repository:** <https://github.com/michaelfeng/CoreMemory-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": "michaelfeng-corememory-mcp"
    }
  }
}
```

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