memory vs BloodHound-MCP-AI
Side-by-side comparison to help you pick between these two MCP servers.
memory by modelcontextprotocol | BloodHound-MCP-AI by MorDavid | |
|---|---|---|
| Stars | ★ 85,748 | ★ 353 |
| 30d uses | — | — |
| Score | 77 | 47 |
| Official | ✓ | — |
| Categories | Knowledge GraphAI / LLM ToolsProductivity | SecurityKnowledge GraphDeveloper Tools |
| Language | TypeScript | Python |
| Last commit | this month | 12 mo ago |
memory · Summary
An MCP server implementing persistent memory using a local knowledge graph for AI models to remember user information across chats.
BloodHound-MCP-AI · Summary
MCP server connecting BloodHound with AI for natural language Active Directory security analysis.
memory · Use cases
- Personalizing AI assistant interactions by remembering user preferences, history, and relationships
- Building context-aware chat applications that maintain conversation history
- Creating knowledge bases that persist across AI model sessions
BloodHound-MCP-AI · Use cases
- Visualize and analyze Active Directory attack paths without knowing Cypher queries
- Assess AD security posture by identifying potential privilege escalation paths
- Generate comprehensive security reports for stakeholders using natural language
memory · Install
Installation
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}VS Code
Use one-click installation buttons or manually configure in .vscode/mcp.json:
{
"servers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Docker
{
"mcpServers": {
"memory": {
"command": "docker",
"args": ["run", "-i", "-v", "claude-memory:/app/dist", "--rm", "mcp/memory"]
}
}
}BloodHound-MCP-AI · Install
Installation
- Clone this repository:
``bash git clone https://github.com/MorDavid/BloodHound-MCP-AI.git cd BloodHound-MCP-AI ``
- Install dependencies:
``bash pip install -r requirements.txt ``
- Configure the MCP Server in Claude Desktop:
```json { "mcpServers": { "BloodHound-MCP": { "command": "python", "args": [ "<Your_Path>\\BloodHound-MCP.py" ], "env": { "BLOODHOUND_URI": "bolt://localhost:7687", "BLOODHOUND_USERNAME": "neo4j", "BLOODHOUND_PASSWORD": "bloodhoundcommunityedition" } } } }