data-ai MCP Server
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Score
Store a new person, project, concept, or any typed node
Get stats on your memory graph — node counts, edge density, orphans
No
100%
Semantic + graph hybrid search across all memories
Dragon Brain
100%
Link two entities with a typed, weighted edge
mcp-knowledge-graph
100%
Explore what's directly connected to an entity
—
~85%
What It Does
Discover missing relationships via vector-graph gap analysis
No
Questions
Attach a fact or note to an existing entity
What's In It
—
91.4%
100%
Query the graph as it existed at a specific timestamp
—
100%
Mark a significant learning moment for future reference
How It Works
95.4%
133
Get an entity with its full connected context (neighbors, observations, relationships)