The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via npm + OpenVSX + Anthropic plugin directory. 89% measured token reduction. Local SQLite, zero cloud, Apache 2.0.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add engram --env ENGRAM_API_TOKEN='<ENGRAM_API_TOKEN>' -- npx -y engramx~/.codex/config.toml
[mcp_servers.engram]
command = "npx"
args = ["-y", "engramx"]
env = { ENGRAM_API_TOKEN = "<ENGRAM_API_TOKEN>" }
# codex mcp add engram --env ENGRAM_API_TOKEN='<ENGRAM_API_TOKEN>' -- npx -y engramx~/.cursor/mcp.json
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engramx"
],
"env": {
"ENGRAM_API_TOKEN": "<ENGRAM_API_TOKEN>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"engram": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"engramx"
],
"env": {
"ENGRAM_API_TOKEN": "<ENGRAM_API_TOKEN>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engramx"
],
"env": {
"ENGRAM_API_TOKEN": "<ENGRAM_API_TOKEN>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engramx"
],
"env": {
"ENGRAM_API_TOKEN": "<ENGRAM_API_TOKEN>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engramx"
],
"env": {
"ENGRAM_API_TOKEN": "<ENGRAM_API_TOKEN>"
}
}
}
}Environment variables
ENGRAM_API_TOKEN
Replace the placeholders with your own credentials and keep them out of version control.