MCP
This page is about an MCP server for this documentation site - it lets an AI agent search and read these docs. It is not the MCP server for the Dime.Scheduler application. To let an agent work with your planning data (tasks, appointments, resources), see the application MCP server instead.
Point an AI agent at the Dime.Scheduler documentation and let it search and read the pages directly. The docs are exposed as a Model Context Protocol (MCP) server, so agents call tools instead of scraping HTML.
The endpoint is:
https://docs.dimescheduler.com/api/mcp
It exposes two tools:
| Tool | Purpose |
|---|---|
docs_search | Full-text search across all documentation pages. Returns titles, URLs and snippets ranked by relevance. |
docs_fetch | Retrieve the full markdown of a specific page by URL. |
The server runs in stateless mode - every request is independent, no session is needed.
Add to Claude Code
claude mcp add --transport http dimescheduler-docs https://docs.dimescheduler.com/api/mcp
In any Claude Code session, ask Claude to search the Dime.Scheduler docs and it will call the MCP tools automatically.
Other MCP clients
The endpoint follows the Streamable HTTP transport from the MCP specification. Any MCP-compatible client can connect: point it at the URL above.
Test with curl
List the available tools:
curl -X POST https://docs.dimescheduler.com/api/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Run a search:
curl -X POST https://docs.dimescheduler.com/api/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"docs_search","arguments":{"query":"business central setup","limit":3}}}'
A GET request returns a status object - useful as a liveness check. The search index loads lazily on the first POST, so a fresh GET will report initialized: false until a real MCP call has been made against the same instance.