Context Engine
local MCP serverContext Engine is a local MCP server: Compress logs, retrieval chunks, and code context into structured LLM-ready signal. Install it from pypi as melonelish-context-engine.
Installation
Terminal
claude mcp add context-engine -- uvx melonelish-context-engine
Run in your project folder. Add --scope user to use it everywhere.
Claude Desktop, Cursor & other clients
Add to claude_desktop_config.json or .cursor/mcp.json.
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}What you need
- Runtime: Python with uv (runs with uvx).
- MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
Summary
Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
Context Engine vs similar servers
| Server | Stars | Type | API key | Runtime |
|---|---|---|---|---|
| Context Engine | 352 | Local | No | pypi |
| RevoGrid DataGrid MCP | 3,446 | Hosted | No | None |
| Entroly | 470 | Local | Yes | pypi |
| Serena MCP: the IDE for your agent | 30K | Local | No | pypi |
| Honcho | 7,369 | Hosted | Yes | None |
Questions
No. The registry entry lists no keys or environment variables.
Python with uv (runs with uvx), plus an MCP client such as Claude Code, Codex, Claude Desktop or Cursor.
Context Engine is a local MCP server distributed as the pypi package melonelish-context-engine.
Run: claude mcp add context-engine -- uvx melonelish-context-engine
Run: codex mcp add context-engine -- uvx melonelish-context-engine
Similar MCP servers
NameStars
- RevoGrid DataGrid MCPio.github.revolist/revogrid-mcp3,446
- Entrolyio.github.juyterman1000/entroly470
- Serena MCP: the IDE for your agentio.github.oraios/serena30K
- Honchoio.github.plastic-labs/honcho7,369
- Agent-Native Planio.github.BuilderIO/agent-native-plan6,874
- ha-mcpio.github.homeassistant-ai/ha-mcp4,868
- mcp-server-chartio.github.antvis/mcp-server-chart4,385
- semio.github.Ataraxy-Labs/sem3,364