Search and read the Druxt documentation and API reference.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Read one Druxt documentation page as markdown, by its path, such as /how-to/proxy.
The page path.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http docs https://druxtjs.org/mcp
Read one Druxt documentation page as markdown, by its path, such as /how-to/proxy.
| Argument | Type | Description |
|---|---|---|
| path* | string | The page path. |
{
"type": "object",
"required": [
"path"
],
"properties": {
"path": {
"type": "string",
"description": "The page path."
}
}
}List Druxt documentation pages, optionally for one section.
| Argument | Type | Description |
|---|---|---|
| section | string |
{
"type": "object",
"properties": {
"section": {
"enum": [
"tutorials",
"how-to",
"explanation",
"modules",
"api"
],
"type": "string"
}
}
}Search the Druxt documentation and API reference. Returns matching pages with their paths.
| Argument | Type | Description |
|---|---|---|
| query* | string | The words to search for. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "The words to search for."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.