memory
Local-first project memory for AI coding agents.
Install memory in your MCP client
memory is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.
- Locate your client's MCP config file.
- Cursor:
~/.cursor/mcp.json - Claude Desktop (macOS):
~/Library/Application Support/Claude/claude_desktop_config.json - Claude Desktop (Windows):
%APPDATA%\Claude\claude_desktop_config.json - VS Code:
Settings → Extensions → MCP - Windsurf:
Settings → MCP Servers
- Cursor:
- Add memory to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing
mcpServersobject. - Restart your client so it picks up the new server.
- Verify — ask the assistant to list available tools; memory's tools should appear.
{
"mcpServers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@aictx/memory"
]
}
}
}Install memory in Cursor
Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. memory will show up in the assistant's tool list on next launch.
Install memory in Claude Desktop (macOS)
Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). memory will show up in the assistant's tool list on next launch.
Install memory in Claude Desktop (Windows)
Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). memory will show up in the assistant's tool list on next launch.
Install memory in VS Code
Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. memory will show up in the assistant's tool list on next launch.
npm package: @aictx/memory
Transport
memory supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.
From the memory README
More build.protocol_tooling.mcp MCP servers
Other Model Context Protocol servers in the same space as memory. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.
musea-mcp-server
MCP server for building Vue.js design systems - component analysis, documentation, variant generation, and design tokens
mcp
Avallon API MCP server - generated from OpenAPI
flow-nexus
🚀 AI-Powered Swarm Intelligence Platform - Gamified MCP Development with 70+ Tools
mcp-server
MCP server for the UnClick tool marketplace — lets AI agents discover and use every UnClick tool
glassbox-framework
Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.
iso27001-mcp
ISO 27001 compliance workspace for Claude. Risks, policies, SoA, evidence, and audit workflows.
Silicon Analysts
Semiconductor data: AI accelerator costs, HBM, wafer pricing, packaging, chip cost calculator.
mcp-pronto
B2B sales intelligence: find companies, extract leads, enrich contacts with emails/phones.
Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.