Search and read the pracht framework documentation: guides, recipes, 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.
The table of contents of the pracht documentation: every page with its path, title, URL, and one-line summary, grouped like the site navigation.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http pracht-docs https://pracht.resynapse.dev/mcp
The table of contents of the pracht documentation: every page with its path, title, URL, and one-line summary, grouped like the site navigation.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Return one page of the pracht documentation as Markdown, or only one section of it. `page` accepts a path (/docs/capabilities), a slug (capabilities, recipes/auth), or a page URL. A whole-page read lists the page's anchors in `sections`. An unknown page or section answers found: false with the closest matches.
| Argument | Type | Description |
|---|---|---|
| page* | string | Page path, slug, or URL, e.g. /docs/capabilities. |
| section | string | Heading anchor from docs_search or `sections`, e.g. remote-mcp-tools-for-agents-without-a-browser. Empty or omitted reads the whole page. |
{
"type": "object",
"required": [
"page"
],
"properties": {
"page": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "Page path, slug, or URL, e.g. /docs/capabilities."
},
"section": {
"type": "string",
"maxLength": 200,
"description": "Heading anchor from docs_search or `sections`, e.g. remote-mcp-tools-for-agents-without-a-browser. Empty or omitted reads the whole page."
}
},
"additionalProperties": false
}Full-text search over the pracht framework documentation at https://pracht.resynapse.dev. Returns the best-matching page sections, each with its page path, section anchor, URL, and a snippet. Pass a result's `page` and `section` to docs_read for the full text.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum number of results. |
| query* | string | Words to look for, e.g. `remote mcp oauth` or `defineApp agents`. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 8,
"maximum": 20,
"minimum": 1,
"description": "Maximum number of results."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Words to look for, e.g. `remote mcp oauth` or `defineApp agents`."
}
},
"additionalProperties": false
}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 11, 2026.