mcp-server vs memory
Side-by-side comparison to help you pick between these two MCP servers.
mcp-server by keboola | memory by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 84 | ★ 85,748 |
| 30d uses | — | — |
| Score | 46 | 77 |
| Official | — | ✓ |
| Categories | DatabaseDeveloper ToolsProductivity | Knowledge GraphAI / LLM ToolsProductivity |
| Language | Python | TypeScript |
| Last commit | this month | this month |
mcp-server · Summary
Keboola MCP Server bridges AI agents with Keboola platform, exposing data, SQL queries, and job triggers as MCP tools.
memory · Summary
An MCP server implementing persistent memory using a local knowledge graph for AI models to remember user information across chats.
mcp-server · Use cases
- AI agents access and query Keboola data tables directly using MCP tools
- Natural language creation of SQL transformations within AI assistants
- Building automated data workflows triggered by AI agents
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
mcp-server · Install
Installation
Remote MCP Server (Recommended)
- Navigate to your Keboola Project Settings →
MCP Servertab - Copy the server URL (format:
https://mcp.<YOUR_REGION>.keboola.com/mcp) - Configure your AI assistant with the URL
- Authenticate with your Keboola account
Claude Desktop Integration
{
"mcpServers": {
"keboola": {
"command": "http",
"args": ["https://mcp.<YOUR_REGION>.keboola.com/mcp"]
}
}
}Local Development
- Install Python 3.10+ and
uv - Clone the repository
- Set environment variables:
- KBC_STORAGE_TOKEN - KBC_STORAGE_API_URL - KBC_WORKSPACE_SCHEMA - Optional: KBC_BRANCH_ID
- Start the server:
``bash python -m mcp_server --transport <stdio|streamable-http> ``
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"]
}
}
}