Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Coding agent with basic read, write and command line tools.
Self-hosted AI teammate in Slack: @mention it and Claude Code or Codex investigates CloudWatch logs, runs tests, and opens pull requests. The bundled MCP server holds all credentials (GitHub, AWS, Slack) so the agent never sees keys. One-command deploy to your own AWS. MIT.
Quality signal
39/100 (Emerging)
43/100 (Fair)
Install path
uvx · high
npx · high
Engagement
4 0 0 1,606
0 0 0 2
Tools
Direct file editing by AI agentPredeclared shell commands executionGit versioning of all AI editsAuto-accept changes by defaultIDE-agnostic designSupports remote server hosting with network binding