Tessera Analytics — the Hyperliquid MCP server
Point Claude — or any MCP client — at the Tessera Hyperliquid MCP server and ask market questions in plain language. Nine tools: discover the catalog and the field vocabulary, then rank the cross-section, screen on several conditions, measure funding divergence, pull per-coin series and read the live market — all authed with your API key.
What it is
The Model Context Protocol lets an AI assistant call external tools. Our hosted Hyperliquid MCP server exposes Tessera Analytics
as a small set of market-intelligence tools, so instead of writing download scripts you can just
ask — "what's BTC trading at right now?" or "which coins are most crowded on funding?" — and the model calls the right tool and reasons over the result. It's a single hosted endpoint
(https://tesseralytics.dev/mcp), authed with the same API key you use for
the REST API.
Installation
First, create an API key on your account page. Then wire it into your client — replace YOUR_TESSERA_API_KEY with your key.
Tools
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 fresh the data is
The daily tools serve complete UTC days only — a day is available once it
has closed, and the day still in progress is never served. Leave the day out or pass latest and the tool resolves to the last complete day,
telling you in the response when it substituted; 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. Every keyed response states the day it covers, the
market scope it ranked, and how many coins the statistics were computed over.
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
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.
Example prompts
Once connected, drive it in natural language — each question maps to one tool. A few things to try:
The model calls query_cross_section with order_by on funding, descending, and top_n — no day given, so it resolves to the
last complete day and the response says which day that is. Add stat=percentile to rank by the percentile within
your visible slice instead of the raw rate.
A multivariate screen: one call to screen_universe with two conditions — funding
in the top decile and the change in open interest in the bottom decile. Both deciles
are computed inside the coins you can see, and the response tells you how many coins matched
versus how many were ranked.
funding_divergence over a 30-day window with ETH
as the benchmark, ranked by divergence: either the average rate spread or the cumulative
spread, your choice. Coins with no funding in the window are excluded from the ranking rather
than shown as zero.
Another screen_universe call: open interest rising
over the trailing week, paired with funding in the bottom decile. A positioning screen like
this is exactly what the daily grain is for — the crowded side shows up in the cross-section
before it shows up in price.
get_universe returns the coverage picture: the
last complete day, how many coins are in the market for each scope, row density and
completeness flags. It's a summary by default; ask for the coin list and it's limited
to the top 50, alphabetically, with a note saying so. The default scope is crypto; pass hip3 for HIP-3 markets
(which carry a venue prefix like xyz:NVDA and, because
they track an underlying that closes, come with a session caveat — their weekend flow isn't
comparable).
query_series for BTC over a 7-day trailing window,
returning return, volume, taker flow and open-interest change per day. The response always
notes how many days the trailing-window figures were computed over, and asks for fewer coins
or a shorter window rather than silently truncating if the payload would blow the row cap.
live_market for BTC — mark price, current funding,
open interest, 24-hour volume and premium, as of the moment you ask. This is the only tool
that answers a "right now" question; everything else is a complete day. Pass up to 25 coins
and any coin the venue can't return is dropped with a note explaining why, rather than failing
the whole call.
Because MCP tools compose, you can plug in a second MCP server or skill — say one that reads a venue like Boros or Derive — and ask things like "given Tessera Analytics' cumulative BTC funding for the past month, which Boros funding markets look mispriced?" The model pulls the funding series from Tessera Analytics and cross-references the other tool.
This is a usage example only — the venue connector is yours to bring; Tessera Analytics doesn't ship or endorse one, and none of this is trading advice.