Tessera Analytics

Model Context Protocol

Tessera Analytics MCP server

Point Claude — or any MCP client — at Tessera Analytics' Hyperliquid datasets and explore them in plain language. Discover the catalog, read the data dictionary, and pull actual rows of funding, positioning, and the funding/RV and wallet forecasts, all authed with your API key.

Get an API key Browse the catalog

What it is

The Model Context Protocol lets an AI assistant call external tools. Our hosted MCP server exposes Tessera Analytics' gold datasets as a small set of tools, so instead of writing download scripts you can just ask — "what's the latest funding-innovation forecast for BTC?" — and the model calls read_dataset and reasons over the rows. 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.

Claude Code

One command — native streamable-HTTP transport with a header.

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

Clients with native header auth

For MCP clients that accept a remote URL plus custom headers, add this to your MCP config.

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

Claude Desktop (via mcp-remote)

Some desktop clients don't yet send custom headers to remote servers. The mcp-remote bridge proxies the connection and injects your key. Add this to claude_desktop_config.json, then restart the app.

{ "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" } } } }

Tools

Tool	Arguments	What it does
list_datasets	—	Discover every gold dataset with a one-line summary and the plan (free/pro) each requires.
describe_dataset	asset	Full data dictionary for one dataset: every column’s type, nullability and plain-English meaning.
list_partitions	asset, coin?	Available (coin, month) partitions you can read, filtered to your plan.
read_dataset	asset, coin, month, columns?, limit?, order?	Read actual data rows. Defaults to the latest 200; pass columns + limit (max 1000) to stay in context.
get_download_url	asset, coin, month	A short-lived link to the full parquet partition — the bulk escape hatch beyond read_dataset.

Example prompts

Once connected, drive it in natural language. A few things to try:

"What datasets can I access, and what's in the funding forecast?"

"What's the latest funding-innovation forecast for BTC?"

"Which wallets have the most persistent PnL signal this month? (Pro)"

Compose with another tool to find plays (illustration)

Free vs Pro

Any valid API key can use the MCP server. A free key reads gold_ohlcv_1m and the funding/RV forecast (gold_positioning_funding_factors_1d) for BTC, ETH, SOL and HYPE — enough to explore the forecast end-to-end.

Pro ($50/mo) unlocks every coin (incl. HIP-3), the raw funding and positioning datasets, and the wallet-behaviour factors. Discovery tools show the whole catalog regardless of plan; reading a slice outside your plan returns a clear "requires Pro" message. See Pricing.