Snoze Developers

MCP server

Connect AI agents and MCP clients to a Snoze workspace.

Snoze ships a Model Context Protocol server, so any MCP client — Claude, coding agents, your own tools — can read and act on a workspace. It speaks Streamable HTTP at https://api.snoze.dev/mcp and authenticates with a workspace API key.

Connecting

Paste a key and copy the command for your client, or use the one-click button for Cursor and VS Code:

Filled into the commands below. It never leaves your browser.

Copies the setup command to your clipboard.

The underlying config is the same everywhere — an HTTP server URL plus a bearer token:

{
  "mcpServers": {
    "snoze": {
      "url": "https://api.snoze.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SNOZE_API_KEY"
      }
    }
  }
}

What agents can do

The server exposes tools over the same kernel the app uses: searching the workspace, reading pages and database records, creating and updating items, and running actions. Everything respects the API key's scopes — an agent can never do more than the key allows.

Available tools

Tools ship in four groups, and a key's scopes decide which groups a client sees:

  • Search — full-text and semantic search across every item the key can read.
  • Read — fetch pages, database schemas and records, dashboards, and files.
  • Mutate — create and update items, edit page content, write records.
  • Actions — list and run the workspace's automations, with run status reporting.

The exact tool list is derived from the same registry the assistant uses, and a key's scopes decide which tools a client sees — so the groups above are a map, not a contract.

Resources

Beyond tools, the server exposes workspace items as MCP resources: clients can list snoze://workspace/{workspaceId}/items/{itemId} URIs (with cursor pagination) and read an item's content directly — useful for clients that attach context by resource rather than by tool call.

Safety

High-stakes tools support approval gates: destructive or outward-facing operations pause with an approval prompt before they execute. Tools also carry standard MCP annotations (readOnlyHint, destructiveHint) so clients can apply their own policies. Requests are capped at 1 MB.

On this page