Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add context-engine -- uvx melonelish-context-engine~/.codex/config.toml
[mcp_servers.context-engine]
command = "uvx"
args = ["melonelish-context-engine"]
# codex mcp add context-engine -- uvx melonelish-context-engine~/.cursor/mcp.json
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}.vscode/mcp.json
{
"servers": {
"context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}