memforge memory for VS Code

io.github.volsier/memforge-memory

Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.

client:VS Code transport:stdio runtime:npm

Install memforge memory in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "database-url",
      "description": "DATABASE_URL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "openai-base-url",
      "description": "OPENAI_BASE_URL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "openai-api-key",
      "description": "OPENAI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "openai-embedding-model",
      "description": "OPENAI_EMBEDDING_MODEL",
      "password": true
    }
  ],
  "servers": {
    "memforge-memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@memforgeai/memory-service"
      ],
      "env": {
        "DATABASE_URL": "${input:database-url}",
        "OPENAI_BASE_URL": "${input:openai-base-url}",
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "OPENAI_EMBEDDING_MODEL": "${input:openai-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

memforge memory in other clients

memforge memory MCP server