Knowledge Porridge
ai.knowledgeporridgev0.1.0Updated Sep 29, 2026
A sourced learning map your AI places you on: finds gaps you can't name, teaches step by step.
Overview
AI-generated overview
A remote learning-map service that lets an assistant place a learner on a sourced map, find knowledge gaps, and teach step by step.
- What it does
- Knowledge Porridge is a remote MCP endpoint that provides a sourced learning map. According to its description, it places the user on that map, identifies gaps the user cannot name themselves, and teaches step by step. No individual tools are listed in the manifest, so the exact operations the assistant can call are not documented here.
- When to use it
- Consider it when you want an assistant to support structured, sequential learning rather than one-off answers, for example to diagnose what someone does not yet know and build a path from there. It is less relevant if you only need quick factual lookups.
- Requirements
- A remote MCP endpoint at knowledgeporridge.ai over streamable HTTP. The manifest declares no authentication, no environment variables, and no headers, and no local package or runtime is needed. Network access to the endpoint is required.
Before you install
The manifest declares no authentication, so it is unclear what account or data handling applies, and no tools are listed, so what the assistant can read or change is undocumented. The description mentions a learning map tied to the user, which suggests personal learning data may be sent to the provider. Verify the provider's data practices before connecting.
Installation
In SourceWeft
- Open Knowledge Porridge in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"knowledge-porridge": {
"type": "http",
"url": "https://knowledgeporridge.ai/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v0.1.0LatestSep 29, 2026