← Index

io.github.n24q02m/mnemo-mcp

io.github.n24q02m/mnemo-mcp·v1.24.4·Search
Quality Score
85
/100

Persistent AI memory with hybrid search (FTS5 + semantic) and cross-machine sync.

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "mnemo-mcp": {
      "command": "uvx",
      "args": [
        "mnemo-mcp"
      ],
      "env": {
        "API_KEYS": "<your-api_keys>"
      }
    }
  }
}
Claude Desktop (Docker)
{
  "mcpServers": {
    "mnemo-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/n24q02m/mnemo-mcp:latest"
      ],
      "env": {
        "API_KEYS": "<your-api_keys>"
      }
    }
  }
}
§02  Environment variables
API_KEYS
secret

API keys for cloud embedding (format: ENV_VAR:key). Without this, uses built-in local Qwen3 model.

API_KEYS
secret

API keys for cloud embedding (format: ENV_VAR:key). Without this, uses built-in local Qwen3 model.

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
10
§04  Alternatives in Search