khwanlabs/khwan-mcp vs MCP-Agent
Side-by-side comparison of two Model Context Protocol servers. Pick the right one for Claude Desktop, Claude Code, or Cursor.
Durable memory for coding agents, built around corrections. Captures the moment you correct the agent as a typed event and distils it overnight into a standing
Comparison
| Feature | khwanlabs/khwan-mcp | MCP-Agent |
|---|---|---|
| Pricing | Free | Free |
| Installs | — | — |
| Rating | — | — |
| Verified | — | |
| Hosted | — | — |
| Tools | — | — |
| Category | ai | ai |
| Author | khwanlabs | lastmile-ai |
| Repo | khwanlabs/khwan-mcp | lastmile-ai/mcp-agent |
When to pick khwanlabs/khwan-mcp
Durable memory for coding agents, built around corrections. Captures the moment you correct the agent as a typed event and distils it overnight into a standing rule the next session starts with, rather than only extracting facts. An isolated brain per project instead of one blended profile. Recall and record make no model calls — your client is the model. pip install khwan-mcp
When to pick MCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
Looking for something else? Browse all MCPs or check trending this week.