Context Engine for Cursor
io.github.melonelish/context-engine
Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
client:Cursor
transport:stdio
runtime:pypi
Install Context Engine in Cursor
~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json
{
"mcpServers": {
"context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}
Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs