Zep Cloud

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.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "fshamim-mcp-server-zep-cloud": {
      "command": "python",
      "args": [
        "/path/to/mcp-server-zep-cloud/core/run_server.py"
      ],
      "env": {
        "MCP_HOST": "0.0.0.0",
        "MCP_PORT": "8080",
        "ZEP_API_KEY": "your_api_key_here"
      }
    }
  }
}

You can store, retrieve, and manage memories and preferences for AI assistants through a dedicated MCP server that connects to the Zep Cloud API. This server acts as a semantic memory layer, helping your AI agents remember users and maintain context across conversations.

How to use

Your MCP client can interact with the Zep Cloud MCP Server to perform memory-related operations. Use the memory store to save user memories, retrieve context for ongoing conversations, search a user’s memory graph, and manage user metadata. When connected, you can rely on the server to handle memory graphs and ensure context persists across sessions, improving assistant consistency and personalization.

How to install

Prerequisites: you should have Python installed to run the MCP server locally. You may also use Docker to run the server in a container.

# Install via Smithery (recommended for quick setup)
npx @smithery/cli install mcp-server-zep-cloud --client claude

Manual installation with Claude Desktop involves cloning the project, installing dependencies, and configuring Claude Desktop to point at the local server.

# Clone the repository
git clone https://github.com/yourusername/mcp-server-zep-cloud.git
cd mcp-server-zep-cloud

# Install dependencies
pip install -r config/requirements.txt

Configure Claude Desktop by adding a MCP server entry to claude_desktop_config.json using the following structure. Replace the path and API key with your actual values.

{
  "mcpServers": {
    "zep-cloud": {
      "command": "python",
      "args": ["/path/to/mcp-server-zep-cloud/core/run_server.py"],
      "env": {
        "ZEP_API_KEY": "your_api_key_here"
      }
    }
  }
}

The configuration file locations for Claude Desktop are:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Using Docker you can build and run the MCP server in a container. The container exposes port 8080 by default.

# Build the container
docker build -t mcp-server-zep-cloud .

# Run the container
docker run -p 8080:8080 \
  -e ZEP_API_KEY="your-api-key" \
  mcp-server-zep-cloud

Additional configuration and notes

Fallback mode activates automatically if the server cannot connect to the Zep Cloud API. In fallback mode, all API operations are simulated and return success, no data is sent to the API, and the server remains operational for client integrations. Warning messages are logged to indicate fallback mode.

Security considerations

Protect your API key by never committing it to version control. Use environment variables for sensitive data and restrict access to trusted networks.

Development and testing

To run tests during development, execute the test suite for the Zep Cloud client and server initialization checks.

Available tools

create_user

Create a new user in Zep Cloud and initialize their memory space.

get_user

Retrieve details for a specific user.

update_user

Update a user's metadata or preferences.

delete_user

Remove a user from Zep Cloud and delete their memories.

list_users

List all users available in the Zep Cloud memory system.

search_graph

Search within a user's memory graph for memories, relations, and entities.

add_graph_data

Add data to a user's memory graph to expand context and relationships.

check_connection

Verify connectivity and status between the MCP server and the Zep Cloud API.

Built by

VeilStrat

AI signals for GTM teams