Agent Skills

MCP ZepAi

A server for Zep, a long-term memory store for AI applications, requiring a ZEP_API_KEY for access.

Install

Install and configure the MCP from https://github.com/annamariakv/Mcp-ZepAi now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.
README

MCP ZepAi Server

This repository contains the MCP (Model Context Protocol) server for the ZepAi module. The server is configured to run using a specific command and environment variables as detailed below.

Configuration

Below is an example configuration:

{
  "mcpServers": {
    "zepai": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "<path_to_the_mcp_directory>",
        "python",
        "-m",
        "mcp_zepai"
      ],
      "cwd": "<path_to_the_mcp_directory>",
      "env": {
        "ZEP_API_KEY": "<your_api_key_here>"
      }
    }
  }
}

Key Configuration Elements

  • command: The command to execute the server, in this case, using uv.
  • args: Arguments passed to the command, including the directory and module to run.
  • cwd: The current working directory for the server.
  • env: Environment variables required for the server, such as ZEP_API_KEY.

Running the Server

To run the MCP ZepAi server, ensure that the configuration file is correctly set up and execute the following command:

/opt/homebrew/bin/uv run --directory <path_to_mcp_directory> python -m mcp_zepai

Ensure that the ZEP_API_KEY environment variable is set with a valid API key.

Search skills and MCP servers

Search across 31,816 skills and MCPs