MCP server for project memory — AI agents record decisions, pitfalls, and specs as they work, and recall them next session with code context. Built for agents, not humans.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add linklore -- uvx llre~/.codex/config.toml
[mcp_servers.linklore]
command = "uvx"
args = ["llre"]
# codex mcp add linklore -- uvx llre~/.cursor/mcp.json
{
"mcpServers": {
"linklore": {
"command": "uvx",
"args": [
"llre"
]
}
}
}.vscode/mcp.json
{
"servers": {
"linklore": {
"type": "stdio",
"command": "uvx",
"args": [
"llre"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"linklore": {
"command": "uvx",
"args": [
"llre"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"linklore": {
"command": "uvx",
"args": [
"llre"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"linklore": {
"command": "uvx",
"args": [
"llre"
]
}
}
}