SuperLocalMemory works with 17+ IDEs via the Model Context Protocol (MCP). The fastest way to connect is auto-detection.

slm connect # Auto-detect and configure all installed IDEs
slm connect --list # See which IDEs are configured

After running, restart your IDE to activate the connection.

If auto-detection does not find your IDE, configure it manually. All IDEs use the same MCP server command:

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Below are the config file paths for each IDE.

Config file: ~/.claude.json (or project-level .mcp.json)

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Config file: ~/.cursor/mcp.json

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Config file: ~/.vscode/mcp.json

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Config file: ~/.codeium/windsurf/mcp_config.json

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Config file: ~/.gemini/settings.json

{
 "mcpServers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
}

Settings > Tools > AI Assistant > MCP Servers:

• Name: superlocalmemory
• Command: slm
• Args: mcp

Config file: ~/.continue/config.json

{
 "mcpServers": [
 {
 "name": "superlocalmemory",
 "command": "slm",
 "args": ["mcp"]
 }
 ]
}

Config file: ~/.config/zed/settings.json

{
 "language_models": {
 "mcp_servers": {
 "superlocalmemory": {
 "command": "slm",
 "args": ["mcp"]
 }
 }
 }
}

After configuring your IDE:

slm status # Check SLM is running
slm connect --list # See which IDEs are configured

In your IDE, try asking your AI: "What do you know about my recent work?" If SuperLocalMemory is connected and has stored memories, the AI will reference them.

IDE does not detect SuperLocalMemory:

• Verify installation: which slm should return a path
• Verify the MCP server starts: slm mcp (should hang waiting for stdio input — Ctrl+C to stop)
• Check your IDE's MCP config file path is correct

Memories not appearing in AI responses:

• Check that you have stored memories: slm recall "test"
• Check the active profile: slm profile list
• Restart your IDE after config changes

Multiple IDEs: All IDEs share the same memory database. A memory stored via Claude Code is available in Cursor, VS Code, and every other connected IDE.

Part of Qualixar | Created by Varun Pratap Bhardwaj