Connect via MCP
Anthra speaks the Model Context Protocol over Streamable HTTP at /api/mcp. Any MCP-compatible client (Claude Desktop, Cursor, Claude Code, Continue, …) can authenticate with one of your personal access tokens and call Anthra’s tools.
Endpoint
URL: https://anthra.vercel.app/api/mcp
Method: POST (JSON-RPC)
Auth: Authorization: Bearer ant_live_…
Protocol revision: 2025-06-18Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your OS:
{
"mcpServers": {
"anthra": {
"url": "https://anthra.vercel.app/api/mcp",
"headers": {
"Authorization": "Bearer ant_live_…"
}
}
}
}Restart Claude Desktop. You should see anthra appear in the tools list with entries like create_book, generate_outline, write_chapter, and publish_book.
Claude Code
claude mcp add --transport http anthra \
https://anthra.vercel.app/api/mcp \
--header "Authorization: Bearer ant_live_…"Cursor
In Cursor’s settings → Tools & Integrations → Add MCP Server:
{
"mcpServers": {
"anthra": {
"url": "https://anthra.vercel.app/api/mcp",
"headers": { "Authorization": "Bearer ant_live_…" }
}
}
}What the model can do
The Anthra MCP exposes the same operations as the REST API. The model will:
- List, read, create, and update books (
books:read,books:write). - Generate outlines, write chapters, rewrite with a directive, and synthesize narration (
generation:run). - Publish books and toggle visibility (
publish:write). - Read account usage and reader analytics (
account:read,analytics:read).
Tools that mutate or spend tokens are gated behind their scope — a key without generation:run can still let the model list and read your books but won’t allow generation.
Recommended scopes for a chat-only client
books:read
books:write
generation:run
publish:writeAdd account:read and analytics:read if you want the model to reason about spend or reader behaviour.
See the full tool reference for every operation, its arguments, and which scope it requires.