hot memory mcp for VS Code

io.github.michael-denyer/hot-memory-mcp

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

client:VS Code transport:stdio runtime:pypi

Install hot memory mcp in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "memory-mcp-db-path",
      "description": "MEMORY_MCP_DB_PATH",
      "password": true
    },
    {
      "type": "promptString",
      "id": "memory-mcp-embedding-model",
      "description": "MEMORY_MCP_EMBEDDING_MODEL",
      "password": true
    }
  ],
  "servers": {
    "hot-memory-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "hot-memory-mcp"
      ],
      "env": {
        "MEMORY_MCP_DB_PATH": "${input:memory-mcp-db-path}",
        "MEMORY_MCP_EMBEDDING_MODEL": "${input:memory-mcp-embedding-model}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

hot memory mcp in other clients

hot memory mcp MCP server