Stock-symbol vectors: which listed symbols an event, theme or headline moves, ranked in one call.
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 Embed Stocks: vector embeddings of listed stock symbols and of text in one space, built for the connections a sector label does not carry — which symbols an event, theme or headline moves, including companies it never names. Send sym:TICKER (e.g. sym:AAPL) for a symbol's own vector, or any text (a headline, a theme). With similarity_to_first=true the answer ranks inputs 2..n by cosine to input 1, so 'headline + candidate symbols in, ranked basket out' is one call. 4,096 dimensions, unit length. Up to 64 inputs per call; no account needed; nothing is stored.
list of texts to embed: sym:TICKER for a listed symbol's own vector, anything else is embedded as text; at most 64
base64 (default, float32 little-endian) or float (4,096 numbers)
also return every other input's cosine to the first input, ranked (e.g. first = the headline, the rest = candidate symbols)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http tuatara-embed-stocks https://cymetica.com/mcp/v1/stock-vectors
Tuatara Embed Stocks: vector embeddings of listed stock symbols and of text in one space, built for the connections a sector label does not carry — which symbols an event, theme or headline moves, including companies it never names. Send sym:TICKER (e.g. sym:AAPL) for a symbol's own vector, or any text (a headline, a theme). With similarity_to_first=true the answer ranks inputs 2..n by cosine to input 1, so 'headline + candidate symbols in, ranked basket out' is one call. 4,096 dimensions, unit length. Up to 64 inputs per call; no account needed; nothing is stored.
| Argument | Type | Description |
|---|---|---|
| input* | array | list of texts to embed: sym:TICKER for a listed symbol's own vector, anything else is embedded as text; at most 64 |
| encoding_format | string | base64 (default, float32 little-endian) or float (4,096 numbers) |
| similarity_to_first | boolean | also return every other input's cosine to the first input, ranked (e.g. first = the headline, the rest = candidate symbols) |
{
"type": "object",
"required": [
"input"
],
"properties": {
"input": {
"type": "array",
"description": "list of texts to embed: sym:TICKER for a listed symbol's own vector, anything else is embedded as text; at most 64"
},
"encoding_format": {
"type": "string",
"description": "base64 (default, float32 little-endian) or float (4,096 numbers)"
},
"similarity_to_first": {
"type": "boolean",
"description": "also return every other input's cosine to the first input, ranked (e.g. first = the headline, the rest = candidate symbols)"
}
}
}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 Oct 30, 2026.