Context Engine runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from pypi. Last commit 11 Jul 2026.
Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
Today is the operative word: we check Context Engine every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add context-engine -- uvx melonelish-context-engine
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}
[mcp_servers.context-engine]
command = "uvx"
args = ["melonelish-context-engine"]
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}
{
"servers": {
"context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}
Semantic code retrieval engine with hybrid search, context expansion, and 40+ language support.
Zero-LLM structural code retrieval for AI coding agents, served over MCP.
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Search structured COMPAMIR news in Japanese and English, with links to source reports.
The shared AI context engine for git — save, search, and share the reasoning behind code changes.
Local read-only repository context retrieval for AI coding agents.
Turn YouTube product demos into structured UX flow reports, and compare demos side by side.
Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
Answers built from our own checks of this server.