Context Engine
Context Engine is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Compress logs, retrieval chunks, and code context into structured LLM-ready signal. It has 351 GitHub stars, is released under the MIT license and runs locally with uvx melonelish-context-engine.
- AI & search
- MIT
- Actively maintained
Install Context Engine
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"context-engine": {
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio context-engine -- uvx melonelish-context-engineCursor
{
"mcpServers": {
"context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"melonelish-context-engine"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
About Context Engine
面向 Agent 工作流、RAG 管线、AI Coding 助手的任务感知 Context Compression Layer。 很多 Agent / RAG / AI Coding 系统的问题,不是“没有上下文”,而是“上下文太脏、太长、太乱”。
Similar MCP servers
More ai & search MCP servers
Context7
upstash/context7
Up-to-date code docs for any prompt.
AI & searchTypeScriptFunASR
modelscope/FunASR
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
AI & searchPythonBifrost
maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
AI & searchGoHoncho
plastic-labs/honcho
Memory that reasons: continual learning for stateful agents.
AI & searchPythonSemble
MinishLab/semble
Fast and Accurate Code Search for Agents.
AI & searchPythonExa
exa-labs/exa-mcp-server
Connect AI agents to Exa for web search, content fetching, and multi-step research.
OfficialAI & searchTypeScript
What is Context Engine?
Context Engine is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Compress logs, retrieval chunks, and code context into structured LLM-ready signal. It has 351 GitHub stars, is released under the MIT license and runs locally with uvx melonelish-context-engine. The source code is at github.com/melonelish/context-engine.
How do I install the Context Engine MCP server?
Add the command uvx melonelish-context-engine to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is Context Engine free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is Context Engine actively maintained?
The most recent commit was on Jul 11, 2026. The latest release is v0.1.0, published Jul 11, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.