Docs for AI assistants
Wire the Duraton docs into Claude, Cursor, and other AI tools so your assistant can search and read them.
The docs are published in a machine-readable form so an AI assistant can pull them in as context: an
llms.txt index at /llms.txt, a full single-file dump at
/llms-full.txt, and clean markdown for every page (add
/content.md to a doc's markdown path, e.g. /llms.mdx/docs/guides/quickstart/content.md).
Point a tool at llms.txt
Any tool that understands llms.txt - Cursor's @Docs, for example - can index the docs directly.
Give it this URL:
https://docs.duraton.dev/llms.txtThe index links to the clean markdown for each page, so the tool fetches documentation, not rendered HTML.
Connect over MCP
The docs run as a hosted MCP server over Streamable HTTP, so an assistant can search and fetch them on
demand with nothing to install. It exposes two tools, list_doc_sources and fetch_docs, and is at:
https://docs-mcp.duraton.dev/mcpAdd it to your client:
claude mcp add --transport http duraton-docs https://docs-mcp.duraton.dev/mcpAdd to ~/.cursor/mcp.json (global) or .cursor/mcp.json (one project):
{
"mcpServers": {
"duraton-docs": {
"url": "https://docs-mcp.duraton.dev/mcp"
}
}
}Add to .vscode/mcp.json. VS Code nests servers under a servers key:
{
"servers": {
"duraton-docs": {
"type": "http",
"url": "https://docs-mcp.duraton.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json. Windsurf names the field serverUrl:
{
"mcpServers": {
"duraton-docs": {
"serverUrl": "https://docs-mcp.duraton.dev/mcp"
}
}
}Most other MCP clients read a mcpServers map with an http server:
{
"mcpServers": {
"duraton-docs": {
"type": "http",
"url": "https://docs-mcp.duraton.dev/mcp"
}
}
}Use a stdio server instead
If your client speaks stdio rather than HTTP, mcpdoc serves
the same two tools from the llms.txt.
mcpdoc runs via uvx, so you need uv installed. The command
downloads mcpdoc on first run.
claude mcp add duraton-docs -- uvx --from mcpdoc mcpdoc --urls Duraton:https://docs.duraton.dev/llms.txt --transport stdioAdd to ~/.cursor/mcp.json (global) or .cursor/mcp.json (one project):
{
"mcpServers": {
"duraton-docs": {
"command": "uvx",
"args": ["--from", "mcpdoc", "mcpdoc", "--urls", "Duraton:https://docs.duraton.dev/llms.txt", "--transport", "stdio"]
}
}
}Add to .vscode/mcp.json. VS Code nests servers under a servers key:
{
"servers": {
"duraton-docs": {
"command": "uvx",
"args": ["--from", "mcpdoc", "mcpdoc", "--urls", "Duraton:https://docs.duraton.dev/llms.txt", "--transport", "stdio"]
}
}
}Add to ~/.codex/config.toml:
[mcp_servers.duraton-docs]
command = "uvx"
args = ["--from", "mcpdoc", "mcpdoc", "--urls", "Duraton:https://docs.duraton.dev/llms.txt", "--transport", "stdio"]Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"duraton-docs": {
"command": "uvx",
"args": ["--from", "mcpdoc", "mcpdoc", "--urls", "Duraton:https://docs.duraton.dev/llms.txt", "--transport", "stdio"]
}
}
}Add to claude_desktop_config.json:
{
"mcpServers": {
"duraton-docs": {
"command": "uvx",
"args": ["--from", "mcpdoc", "mcpdoc", "--urls", "Duraton:https://docs.duraton.dev/llms.txt", "--transport", "stdio"]
}
}
}Restart the client, and the assistant can list the docs source and fetch any page on demand.
See the AI examples running end to end in Examples.