memwright

Indexed by io.github.bolnet

About

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Use this server

Add it to your MCP client. The catalogue lists this config verbatim from its source — it does not run, download, or vouch for the server. Review the command before you run it.

Transportstdio (runs a local command)

Env varsPG_CONNECTION_STRING NEO4J_PASSWORD OPENROUTER_API_KEY OPENAI_API_KEY

Claude Code

claude mcp add --env PG_CONNECTION_STRING= --env NEO4J_PASSWORD= --env OPENROUTER_API_KEY= --env OPENAI_API_KEY= memwright -- uvx memwright

Cursor

Add to Cursor

If the button doesn't open Cursor, use the JSON below — Cursor accepts the same mcpServers config.

VS Code

code --add-mcp '{"name":"memwright","command":"uvx","args":["memwright"],"env":{"PG_CONNECTION_STRING":"","NEO4J_PASSWORD":"","OPENROUTER_API_KEY":"","OPENAI_API_KEY":""}}'

JSON

{
  "mcpServers": {
    "memwright": {
      "command": "uvx",
      "args": [
        "memwright"
      ],
      "env": {
        "PG_CONNECTION_STRING": "",
        "NEO4J_PASSWORD": "",
        "OPENROUTER_API_KEY": "",
        "OPENAI_API_KEY": ""
      }
    }
  }
}

Environment variables are listed by name only — fill in your own values. Entries never carry secrets.