io.github.DiaaAj/a-mem-mcp MCP Server

Name: io.github.DiaaAj/a-mem-mcp MCP Server
Author: io.github.DiaaAj

io.github.DiaaAj/a-mem-mcp

Repository Registry

What is the io.github.DiaaAj/a-mem-mcp MCP server?

Self-evolving memory system for AI agents

How to install io.github.DiaaAj/a-mem-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

LLM_BACKEND
LLM backend to use (openai, ollama, sglang, or openrouter)
LLM_MODEL
LLM model name (e.g., gpt-4o-mini, llama2, etc.)
OPENAI_API_KEY
required
secret
OpenAI API key (required if LLM_BACKEND=openai)
EMBEDDING_MODEL
Sentence transformer model for embeddings
CHROMA_DB_PATH
ChromaDB storage directory path

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "a-mem-mcp": {
      "command": "uvx",
      "args": [
        "a-mem"
      ],
      "env": {
        "LLM_BACKEND": "<YOUR_LLM_BACKEND>",
        "LLM_MODEL": "<YOUR_LLM_MODEL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
        "CHROMA_DB_PATH": "<YOUR_CHROMA_DB_PATH>"
      }
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "a-mem-mcp": {
      "command": "uvx",
      "args": [
        "a-mem"
      ],
      "env": {
        "LLM_BACKEND": "<YOUR_LLM_BACKEND>",
        "LLM_MODEL": "<YOUR_LLM_MODEL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
        "CHROMA_DB_PATH": "<YOUR_CHROMA_DB_PATH>"
      }
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "a-mem-mcp": {
      "command": "uvx",
      "args": [
        "a-mem"
      ],
      "env": {
        "LLM_BACKEND": "<YOUR_LLM_BACKEND>",
        "LLM_MODEL": "<YOUR_LLM_MODEL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
        "CHROMA_DB_PATH": "<YOUR_CHROMA_DB_PATH>"
      }
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "a-mem-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "a-mem"
      ],
      "env": {
        "LLM_BACKEND": "<YOUR_LLM_BACKEND>",
        "LLM_MODEL": "<YOUR_LLM_MODEL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
        "CHROMA_DB_PATH": "<YOUR_CHROMA_DB_PATH>"
      }
    }
  }
}

Claude Code

claude mcp add a-mem-mcp --env LLM_BACKEND=<YOUR_LLM_BACKEND> --env LLM_MODEL=<YOUR_LLM_MODEL> --env OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> --env EMBEDDING_MODEL=<YOUR_EMBEDDING_MODEL> --env CHROMA_DB_PATH=<YOUR_CHROMA_DB_PATH> -- uvx a-mem