1. Home
  2. Basic Memory
  3. Basic Memory for Cursor: Setup & Config

Data as of

Basic Memory for Cursor: Setup & Config

Cursor: Basic Memory gives AI clients persistent knowledge stored as Markdown that people can also edit.

What you can do with Basic Memory in Cursor

Persistent AI knowledge in editable Markdown, with local ownership and optional cloud teamwork.

  • Use Obsidian and an AI assistant on the same knowledge files.
  • Share team notes through the optional cloud workspace.

Before you start: Basic Memory in Cursor

  • Python 3.12+
  • uv / uvx
  • An MCP-compatible client

This is the local client configuration from the README. Notes default to ~/basic-memory. Optional cloud onboarding is separate; no cloud MCP endpoint is specified in the supplied README.

Basic Memory Cursor configuration

  1. Choose Cursor configuration scope

    For Basic Memory, open Project: .cursor/mcp.json User: ~/.cursor/mcp.json. Merge into mcpServers at project or user scope.

  2. Add Basic Memory to Cursor

    Use the basic-memory entry below in mcpServers. Keep Basic Memory's documented stdio connection fields and your other Cursor entries.

  3. Check Basic Memory in Cursor

    Basic Memory: Enable in Cursor’s MCP settings; inspect tools.

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

JSON
{
  "mcpServers": {
    "basic-memory": {
      "command": "uvx",
      "args": [
        "basic-memory",
        "mcp"
      ],
      "env": {}
    }
  }
}

Basic Memory tools available to Cursor

Basic Memory's stored tool list documents 7 tools; compare it with Cursor's connected tool list, because the stored list is not a live check.

search

Find search under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Search knowledge through the documented ChatGPT-compatible action interface.

fetch

Find fetch under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

schema_infer

Find schema_infer under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

schema_validate

Find schema_validate under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

schema_diff

Find schema_diff under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Compare knowledge-base structure changes.

edit_note

Find edit_note under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Edit notes, including append and prepend operations.

write_note

Find write_note under Basic Memory in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Write a note with protection against unintended overwrites.

Basic Memory: full stored tool descriptions

Troubleshooting Basic Memory in Cursor

  • Cursor must find uvx basic-memory (from uv, for Python tools) for Basic Memory. Enable the project/user entry in MCP settings and inspect its tools.
  • Basic Memory uses stdio here: Cursor must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
  • Known limitation: Local users manage their own backups and cross-device sync.
  • Known limitation: Cloud hosting is a paid option.
  • Known limitation: The local install requires Python.
  • General Cursor troubleshooting lives in the /clients/cursor guide.

Basic Memory — details. Cursor guide

Frequently asked questions

Cursor's Basic Memory entry belongs under mcpServers in .cursor/mcp.json (project) or ~/.cursor/mcp.json (user). Confirm the active scope in MCP settings.

Cursor's basic-memory example uses stdio.

Basic Memory's Cursor configuration invokes uvx basic-memory (from uv, for Python tools).

Basic Memory's stored list contains 7 tools, including search, fetch, schema_infer. Compare those names with Cursor's connected tool list; the stored list is not a live check.

No. The local engine is free and supports offline, air-gapped use.

No. The plugin requires an existing Basic Memory MCP connection.

The README identifies AGPL-3.0 for both local and cloud source code.