The topics in a set of documents in one call, with each document's topic mixture. Nothing stored.
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.
Tuatara Topics: find the topics in a set of documents. Returns num_topics topics, each with its words, a label, a description and a weight, plus every document's topic mixture, in one call; a dictionary model's word knowledge guides a probabilistic topic model, so topics are coherent on small sets and short texts. Nothing is trained on or kept from the request. 4 to 500 documents of up to 20,000 characters per call.
the documents (plain text), 4 to 500
give each topic a short label and description (default true)
words per topic, 3-30 (default 15)
topics to find, 2-100 and at most half the number of documents (default 10)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http tuatara-topics https://cymetica.com/mcp/v1/topics
Tuatara Topics: find the topics in a set of documents. Returns num_topics topics, each with its words, a label, a description and a weight, plus every document's topic mixture, in one call; a dictionary model's word knowledge guides a probabilistic topic model, so topics are coherent on small sets and short texts. Nothing is trained on or kept from the request. 4 to 500 documents of up to 20,000 characters per call.
| Argument | Type | Description |
|---|---|---|
| labels | boolean | give each topic a short label and description (default true) |
| documents* | array | the documents (plain text), 4 to 500 |
| num_words | integer | words per topic, 3-30 (default 15) |
| num_topics | integer | topics to find, 2-100 and at most half the number of documents (default 10) |
{
"type": "object",
"required": [
"documents"
],
"properties": {
"labels": {
"type": "boolean",
"description": "give each topic a short label and description (default true)"
},
"documents": {
"type": "array",
"items": {
"type": "string"
},
"description": "the documents (plain text), 4 to 500"
},
"num_words": {
"type": "integer",
"description": "words per topic, 3-30 (default 15)"
},
"num_topics": {
"type": "integer",
"description": "topics to find, 2-100 and at most half the number of documents (default 10)"
}
}
}Tuatara Topics: place one document on the general topic set (the served model's topics) and return the topics it belongs to with their weights. Nothing is stored.
| Argument | Type | Description |
|---|---|---|
| document* | string | the document (plain text) |
| num_words | integer | words per topic, 3-30 (default 15) |
{
"type": "object",
"required": [
"document"
],
"properties": {
"document": {
"type": "string",
"description": "the document (plain text)"
},
"num_words": {
"type": "integer",
"description": "words per topic, 3-30 (default 15)"
}
}
}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 3, 2026.