Tuatara Topics is answering right now. Last checked 6 min ago. It exposes 2 tools.
The topics in a set of documents in one call, with each document's topic mixture. Nothing stored.
Today is the operative word: we check Tuatara Topics every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add tuatara-topics --transport http https://cymetica.com/mcp/v1/topics
https://cymetica.com/mcp/v1/topics
[mcp_servers.tuatara-topics]
url = "https://cymetica.com/mcp/v1/topics"
{
"mcpServers": {
"tuatara-topics": {
"url": "https://cymetica.com/mcp/v1/topics"
}
}
}
{
"servers": {
"tuatara-topics": {
"type": "http",
"url": "https://cymetica.com/mcp/v1/topics"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
topic_of_document
find_topics
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://cymetica.com/mcp/v1/topics | streamable-http | answering | 979 ms | 6 min ago |
Every match, not the top 10. Searches your documents and returns each relevant one, with quotes.
Operate Notion with a single Markdown document — read, create, and update pages in one call.
Get the US federal tax numbers right, with the IRS document each one comes from.
Score sentiment toward specific entities in text. Cluster documents and name topics.
Inspect, search, fetch, and convert local documents and mail stores with bounded access.
Extractive document summarizer: returns the text's own sentences, so it cannot add facts.
Semantic document memory using Redis vector store. Save and recall files with natural language.
Turn meeting notes or transcripts into a clean structured summary document from chat.
Answers built from our own checks of this server.