loading…
Search for a command to run...
loading…
Side-by-side comparison of two Model Context Protocol servers. Pick the right one for Claude Desktop, Claude Code, or Cursor.
Persistent graph memory for AI agents. Drop a conversation turn in via observeconversation() and facts are auto-extracted, stored as typed graph nodes with loca
| Feature | Abhigyan-Shekhar/Waggle-mcp | Postgres |
|---|---|---|
| Pricing | Free | Free |
| Installs | — | 22,300 |
| Rating | — | 4.8 (412) |
| Verified | — | |
| Hosted | — | — |
| Tools | — | 4 |
| Category | data | data |
| Author | Abhigyan-Shekhar | Anthropic |
| Repo | Abhigyan-Shekhar/Waggle-mcp | — |
Persistent graph memory for AI agents. Drop a conversation turn in via observeconversation() and facts are auto-extracted, stored as typed graph nodes with local semantic embeddings (no API key). Supports temporal queries ("what did we decide last week?"), conflict detection, and context priming. One-command setup with waggle-mcp init. SQLite locally, Neo4j in production.
Connect Claude to any Postgres. Ask questions in English, get SQL + results. Schema-aware, read-only safe mode by default.
Looking for something else? Browse all MCPs or check trending this week.