Universal long-term memory layer for AI coding assistants, powered by EverMemOS.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add evermemos --env EVERMEMOS_API_KEY='<EVERMEMOS_API_KEY>' --env EVERMEMOS_USER_ID='<EVERMEMOS_USER_ID>' -- uvx evermemos-mcp@latest~/.codex/config.toml
[mcp_servers.evermemos]
command = "uvx"
args = ["evermemos-mcp@latest"]
env = { EVERMEMOS_API_KEY = "<EVERMEMOS_API_KEY>", EVERMEMOS_USER_ID = "<EVERMEMOS_USER_ID>" }
# codex mcp add evermemos --env EVERMEMOS_API_KEY='<EVERMEMOS_API_KEY>' --env EVERMEMOS_USER_ID='<EVERMEMOS_USER_ID>' -- uvx evermemos-mcp@latest~/.cursor/mcp.json
{
"mcpServers": {
"evermemos": {
"command": "uvx",
"args": [
"evermemos-mcp@latest"
],
"env": {
"EVERMEMOS_API_KEY": "<EVERMEMOS_API_KEY>",
"EVERMEMOS_USER_ID": "<EVERMEMOS_USER_ID>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"evermemos": {
"type": "stdio",
"command": "uvx",
"args": [
"evermemos-mcp@latest"
],
"env": {
"EVERMEMOS_API_KEY": "<EVERMEMOS_API_KEY>",
"EVERMEMOS_USER_ID": "<EVERMEMOS_USER_ID>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"evermemos": {
"command": "uvx",
"args": [
"evermemos-mcp@latest"
],
"env": {
"EVERMEMOS_API_KEY": "<EVERMEMOS_API_KEY>",
"EVERMEMOS_USER_ID": "<EVERMEMOS_USER_ID>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"evermemos": {
"command": "uvx",
"args": [
"evermemos-mcp@latest"
],
"env": {
"EVERMEMOS_API_KEY": "<EVERMEMOS_API_KEY>",
"EVERMEMOS_USER_ID": "<EVERMEMOS_USER_ID>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"evermemos": {
"command": "uvx",
"args": [
"evermemos-mcp@latest"
],
"env": {
"EVERMEMOS_API_KEY": "<EVERMEMOS_API_KEY>",
"EVERMEMOS_USER_ID": "<EVERMEMOS_USER_ID>"
}
}
}
}Environment variables
EVERMEMOS_API_KEYEVERMEMOS_USER_ID
Replace the placeholders with your own credentials and keep them out of version control.