MCP server

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.

Connecting

Pick your client — the one-click buttons and official commands below need no configuration. The first time the client talks to Snoze, your browser opens to sign in and approve access:

MCP serverhttps://api.snoze.dev/mcpSign in from your client when it first connects — no API key needed.

Claude CodeClaudeCodexCursorVS CodeJSON

This projectAll my projectsWhole teamDefault — just you, this project.

claude mcp add --transport http snoze https://api.snoze.dev/mcp

Then run /mcp inside Claude Code and pick snoze to sign in.

Use an API key instead (scripts & CI)

Two ways to authenticate

OAuth sign-in (default). The server implements the MCP authorization spec: an unauthenticated request returns 401 with a WWW-Authenticate hint pointing at /.well-known/oauth-protected-resource/mcp, and clients discover the authorization server and run the browser sign-in flow from there. The agent acts as the signed-in user — it can read and change exactly what that user's workspace role allows.

Workspace API key. Headless environments (CI, scripts, servers) can't open a browser. Send a workspace API key as a bearer token instead — no sign-in flow, and the agent is capped to the key's scopes rather than a user's full role. Create one at Settings → API keys.

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

Choosing a workspace

API keys are workspace-scoped, so they need nothing extra. With OAuth, the bare URL connects to the signed-in user's oldest workspace, and the server's instructions tell the agent which workspace it landed in (plus the alternatives). To pin a specific workspace, add its slug to the server URL:

https://api.snoze.dev/mcp?workspace=your-workspace-slug

Official install commands

The install card above fills these in; they're reproduced here for reference.

# For you, this project (default scope)
claude mcp add --transport http snoze https://api.snoze.dev/mcp

# For you, every project:            --scope user
# For everyone on the project        --scope project  (commits a shared .mcp.json)

Then run /mcp inside Claude Code to sign in. For Claude on web or desktop, add https://api.snoze.dev/mcp as a custom connector under Settings → Connectors.

codex mcp add snoze --url https://api.snoze.dev/mcp
codex mcp login snoze

code --add-mcp '{"name":"snoze","type":"http","url":"https://api.snoze.dev/mcp"}'

Cursor installs through the one-click button above, or manually under Cursor Settings → MCP with the generic JSON config.

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. Authorization is identical to the product's: an OAuth agent is bounded by the signed-in user's role, an API-key agent by the key's scopes.

Available tools

Tools ship in four groups, and the caller's permissions decide which groups a client sees:

• Search — full-text and semantic search across every item the caller 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 — 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.