The Hyperliquid MCP server for cross-sectional market intelligence

What you can ask, and what comes back

Eight questions the intelligence layer answers today. Each maps to one shipped tool, and each response names the complete day it covers and the slice it ranked.

A raw-row wrapper is not an intelligence layer

Most perp-data MCP servers hand the model rows and leave the thinking to it: a candle, a funding print, an open-interest number. That works for “what’s the funding”, and collapses on “which coins are crowded relative to the rest of the market” — the model can’t rank a universe it can’t hold.

The intelligence layer cannot page raw rows, by design — row access stays on the REST API. Discovery tools need no key; the analytics tools take yours and rank only the slice your plan can see.

Get connected

First create an API key. Then wire it into your client — replace YOUR_TESSERA_API_KEY with your key.

claude mcp add --transport http tessera https://tesseralytics.dev/mcp \
  --header "Authorization: Bearer $TESSERA_API_KEY"

{
  "mcpServers": {
    "tessera": {
      "type": "http",
      "url": "https://tesseralytics.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TESSERA_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "tessera": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://tesseralytics.dev/mcp",
        "--header", "Authorization: Bearer ${TESSERA_API_KEY}"
      ],
      "env": {
        "TESSERA_API_KEY": "YOUR_TESSERA_API_KEY"
      }
    }
  }
}

The nine tools

Three open discovery tools, six keyed analytics tools. Discovery works without a key; the analytics tools take your API key and see only your plan's slice of the market.

Open — no API key

Discovery. These answer before you sign in, so an assistant can learn the vocabulary first.

Keyed — API key required

Analytics. Your key hands the model your plan’s slice of the market; it can’t widen or remove it.

How an answer behaves

Complete UTC days only

A day is available once it has closed, and the day still in progress is never served: name it and the response says as much and serves the last complete day instead. Leave the day out or pass latest and the tool resolves to the last complete day; either way the response names the day it answered for. Ask for a day before or after the covered range and you get an explicit error naming the range rather than silent zeros.

live_market is the only now tool — price, funding and open interest as of the moment you ask, stamped with the moment it was read. Every daily response names the day it answered for and the market scope it ranked, alongside the count that makes the answer legible: markets in scope for a ranking, matches for a screen, days for a series.

Rankings and screens are computed within the coins you can see, so they need a wide enough slice to be meaningful — a one-coin slice is refused instead of returning a hollow percentile.

Fields come from discovery

Field names, meanings and units are not something you memorise: call list_fields (or ask for the vocabulary in plain language) and the model gets every column the query tools accept, each with a plain-English meaning and its unit. Discovery is free — pass those names straight into columns, a screen condition, or order_by.