Dragon Brain

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.

Verified
data-aidata-ai
2 views47 stars7 forksMIT

Why This Matters

Discovered via github-topic:mcp and last synced 3mo ago.

Verified
Source
github-topic:mcp
Stars
47
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
31
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (31)

System

Score

create_entity

Store a new person, project, concept, or any typed node

graph_health

Get stats on your memory graph — node counts, edge density, orphans

No

No

78

100%

search_memory

Semantic + graph hybrid search across all memories

Feature

Dragon Brain

133

100%

create_relationship

Link two entities with a typed, weighted edge

basic-memory

mcp-knowledge-graph

56

100%

get_neighbors

Explore what's directly connected to an entity

34

—

Mem0

~85%

Tool

What It Does

semantic_radar

Discover missing relationships via vector-graph gap analysis

Yes

No

Category

Questions

add_observation

Attach a fact or note to an existing entity

Doc

What's In It

Edges

—

Hindsight

91.4%

30

100%

point_in_time_query

Query the graph as it existed at a specific timestamp

Streamlit

—

70

100%

record_breakthrough

Mark a significant learning moment for future reference

Capability

How It Works

OMEGA

95.4%

Multi-session

133

get_hologram

Get an entity with its full connected context (neighbors, observations, relationships)