mcp.

as i've said: i love to collect things. but a good collection needs to be searchable and retrievable. in the age of ai this becomes more and more important as context becomes the defining factor. so i built myself an mcp server that exposes a vector search based index to all the notes, academic sources, recipes and writing i have.

and if you ever felt the need to ask what fabian knows, here is your chance to also connect your agents to my context and knowledge.

getting started.

add the following url as a remote http mcp server in a compatible client. most clients ask for a name and a server url. the example json shows the common shape; the exact settings screen or configuration syntax depends on the client.

https://www.klinke.studio/api/mcp
{
  "mcpServers": {
    "klinke-studio": {
      "url": "https://www.klinke.studio/api/mcp"
    }
  }
}

once connected, try questions such as:

  • what does fabian mean by truth to material?
  • find notes about sound, emotion and physiological arousal.
  • which writing discusses audio software or mixing?
  • find a recipe that uses mushrooms and lemon.
  • what sources in the bibliography discuss music recommendation?

what the server can do.

{
  "method": "tools/call",
  "params": {
    "name": "search_public_knowledge",
    "arguments": {
      "query": "notes about sound and emotion",
      "kinds": ["note"],
      "limit": 8
    }
  }
}
{
  "method": "tools/call",
  "params": {
    "name": "get_public_document",
    "arguments": {
      "id": "note:audio/digital-musicianship",
      "offsetCharacters": 0,
      "maximumCharacters": 20000
    }
  }
}
{
  "method": "tools/call",
  "params": {
    "name": "get_public_document_chunks",
    "arguments": {
      "id": "note:audio/digital-musicianship",
      "offset": 0,
      "limit": 6
    }
  }
}
{
  "method": "tools/call",
  "params": {
    "name": "get_related_public_documents",
    "arguments": {
      "id": "note:audio/digital-musicianship",
      "limit": 6
    }
  }
}
{
  "method": "tools/call",
  "params": {
    "name": "get_public_knowledge_index_status",
    "arguments": {}
  }
}