Skip to main content
Glama
jaysack

zep-mcp

by jaysack

Zep Cloud MCP Server

An MCP (Model Context Protocol) server that wraps the Zep Cloud API, giving AI assistants long-term memory via Zep's knowledge graph.

Tools

Tool

Description

zep_search_memory

Search a user's knowledge graph for facts

zep_add_note

Add a fact/note to a user's knowledge graph

zep_get_context

Get memory context for a thread (for prompt injection)

zep_add_messages

Store messages in a thread for memory extraction

zep_create_user

Create or ensure a Zep user exists

zep_create_thread

Create a new conversation thread for a user

Related MCP server: Mcp-ZepAi Server

Setup

npm install

Get your API key from Zep Cloud.

Usage

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "zep": {
      "command": "node",
      "args": ["/absolute/path/to/zep-mcp/server.mjs"],
      "env": {
        "ZEP_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "zep": {
      "command": "node",
      "args": ["/absolute/path/to/zep-mcp/server.mjs"],
      "env": {
        "ZEP_API_KEY": "your-api-key"
      }
    }
  }
}

OpenClaw / mcporter

{
  "mcpServers": {
    "zep": {
      "command": "node",
      "args": ["./path/to/zep-mcp/server.mjs"],
      "env": {
        "ZEP_API_KEY": "your-api-key"
      }
    }
  }
}

Standalone

ZEP_API_KEY=your-api-key node server.mjs

The server communicates over stdio using JSON-RPC (MCP protocol).

How It Works

Zep automatically builds a knowledge graph from conversations. The typical workflow:

  1. Create a user → zep_create_user

  2. Create a thread → zep_create_thread

  3. Store messages → zep_add_messages (Zep extracts facts automatically)

  4. Query memories → zep_search_memory or zep_get_context

  5. Add direct notes → zep_add_note (for facts not from conversation)

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Zep Cloud MCP Server: Provides memory management via the Zep Cloud API. Enables storing and retrieving user preferences, procedures, and factual relationships through a knowledge graph. Supports fallback mode for reliable operation when API is unreachable.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that integrates the ZepAi module to provide long-term memory and retrieval capabilities for AI applications. It allows models to interact with Zep's services through a standardized interface using an API key.
    1
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    MCP server that gives AI agents and teams persistent, shared memory using a knowledge graph with vector embeddings, automatic consolidation of related facts, and hybrid search.
    3
    -
  • A
    license
    Not graded
    quality
    A
    maintenance
    A universal MCP server providing persistent, structured memory through a knowledge graph with graph storage, semantic vector search, and multi-hop traversal for AI agents and IDEs.
    1
    MIT