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.
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.
An MCP server that indexes local code into a graph database to provide context to AI assistants with a graphical code visualizations for humans.
Quality signal
43/100 (Fair)
57/100 (Good)
Install path
npx · high
npx · low
Engagement
0 0 0 2
3 0 0 4,055
Tools
Not listed yet
Indexes code using tree-sitter and optional SCIP indexersStores code entities and relationships in a graph databaseProvides a CLI for direct graph queries and analysisRuns an MCP server to serve AI assistants with code contextSupports multiple programming languagesEnables natural language querying of complex code graphs
