Mcp-ZepAi
MCP server for Zep Ai
Documentation
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",
"",
"python",
"-m",
"mcp_zepai"
],
"cwd": "",
"env": {
"ZEP_API_KEY": ""
}
}
}
}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 python -m mcp_zepaiEnsure that the `ZEP_API_KEY` environment variable is set with a valid API key.
Frequently asked questions
What is Mcp-ZepAi?
Mcp-ZepAi is MCP server for Zep Ai
How do I install Mcp-ZepAi?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is Mcp-ZepAi open source?
Yes — it is hosted on GitHub at https://github.com/annamariakv/Mcp-ZepAi and has 1 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP