Ask your AI about these docs

These docs are available as a public, read-only MCP server. Connect it to the AI tool you already use, then ask questions such as “How do I enrol learners with a CSV file in Blend-ed?”. Your AI searches the docs, reads the relevant pages, and answers with links back to them.

https://docs.blend-ed.com/mcp

No account or key is needed. The server speaks streamable-http.

Note

This is the docs MCP server: it only searches and reads documentation. To let an AI manage an Open edX site, see the Open edX MCP.

Claude (claude.ai and Claude Desktop)

1. Open Settings → Connectors and choose Add custom connector.
2. Name it Blend-ed Docs and paste https://docs.blend-ed.com/mcp as the URL.
3. In a chat, enable the connector from the tools menu and ask your question.

Claude Code

claude mcp add --transport http blend-ed-docs https://docs.blend-ed.com/mcp

Cursor

Add the server to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{
  "mcpServers": {
    "blend-ed-docs": { "url": "https://docs.blend-ed.com/mcp" }
  }
}

VS Code

Add the server to .vscode/mcp.json:

{
  "servers": {
    "blend-ed-docs": { "type": "http", "url": "https://docs.blend-ed.com/mcp" }
  }
}

Other MCP clients

Any client that supports remote streamable-http servers can use the URL directly. Clients that only start local stdio servers can bridge with mcp-remote:

{
  "mcpServers": {
    "blend-ed-docs": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://docs.blend-ed.com/mcp"]
    }
  }
}

Tools

Tool	What it does
search_docs	Searches every page and returns the most relevant sections with their URLs.
get_page	Returns the full Markdown of one page, from a URL or a path such as /openedx-mcp/keys/.
list_pages	Lists pages with one-line descriptions, optionally for one section.

Each IP address can make up to 60 requests per minute. The docs are also published as llms.txt and llms-full.txt for tools that read documentation directly.