6ducklearn MCP server
{
"mcpServers": {
"6ducklearn": {
"type": "http",
"url": "https://6ducklearn.com/mcp"
}
}
}{
"mcpServers": {
"6ducklearn": {
"type": "http",
"url": "https://6ducklearn.com/mcp"
}
}
}{
"mcpServers": {
"6ducklearn": {
"type": "http",
"url": "https://6ducklearn.com/mcp"
}
}
}{
"servers": {
"6ducklearn": {
"type": "http",
"url": "https://6ducklearn.com/mcp"
}
}
}{
"mcpServers": {
"6ducklearn": {
"type": "http",
"url": "https://6ducklearn.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 0.1.1
What it does
6DuckLearn MCP connects agents to 6DuckLearn's memory, approval workflows, and runtime control through a hosted endpoint. It is for developers integrating AI agents with 6DuckLearn's research, organization, reminders, portfolio review, and knowledge retrieval capabilities.
- Research and organize financial information, summaries, and alerts through agent-authorized workflows
- Create canvases and retrieve knowledge from 6DuckLearn's stored memory within agent conversations
- Bridge local AI runtimes (Codex, Hermes, OpenClaw) to 6DuckLearn via the AI Runtime Connector
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.