# zep-mcp

> zep-mcp — jaysack-zep-mcp. Use this tool when you need to enhance AI assistants with long-term memory capabilities, storing and searching facts, and managing user interactions. It solves problems of knowledge retention and retrieval, enabling AI agents to learn and recall information over time. The zep-mcp tool takes in API requests and outputs stored knowledge graph data, ideal for use cases requiring persistent memory and user management.

Canonical page: https://skillsregistry.net/skills/jaysack-zep-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jaysack-zep-mcp

## Description

MCP server that wraps the Zep Cloud API to give AI assistants long-term memory via a knowledge graph, enabling storing and searching facts, managing users and threads, and adding notes.

## 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:** search
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/grgzeu6tii)
- **Repository:** <https://github.com/jaysack/zep-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": "jaysack-zep-mcp"
    }
  }
}
```

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