Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.spote.cloud/llms.txt

Use this file to discover all available pages before exploring further.

Spote exposes a built-in MCP (Model Context Protocol) server that lets AI agents like Claude read and write your notes without you leaving the conversation. Once connected, you can tell your agent to save a summary, search for a past decision, or list your recent notes — all through natural language.

​
Step 1: Generate a Personal Access Token

You need a Personal Access Token (PAT) to authenticate your AI agent.
  1. Open Settings in the Spote app.
  2. Go to Tokens and click Create new token.
  3. Give the token a label so you can identify it later — for example, Claude Desktop.
  4. Click Create. Your token appears once in the format spote_<32 hex chars>.
Copy your token immediately and store it somewhere safe. Spote only shows the token value once. If you lose it, delete the token and create a new one.

​
Step 2: Configure your AI tool

Open your Claude Desktop configuration file and add a new entry under mcpServers. Replace spote_YOUR_TOKEN_HERE with the token you just copied.
{
  "mcpServers": {
    "spote": {
      "url": "https://your-spote-app.com/sse",
      "headers": {
        "Authorization": "Bearer spote_YOUR_TOKEN_HERE"
      }
    }
  }
}
Restart Claude Desktop after saving the file. Spote uses the /sse endpoint for Server-Sent Events transport. If your client prefers HTTP streaming, use /mcp instead.

​
Step 3: Test the connection

After saving your configuration and restarting your AI tool, start a new conversation and ask:
  • “List my recent notes in Spote.”
  • “Save a note to Spote titled ‘Test connection’.”
Your agent should respond with note data or confirm that the note was saved. If you see an error, double-check that the token value and endpoint URL are correct, and that you restarted the client after making changes.
Use the MCP tools reference at /mcp/tools to see everything your agent can do — including semantic search, finding similar notes, and listing buckets and tags.